← Back to search
ai.afmr/discovery

AFMR Discovery

Read AFMR failure modes and discover scoped attestation and lift-evidence contracts.

Decision: Allow with approval
Why: exec-capable tools + no confirmation safeguards + high-risk tools need review
Next: export policy, require approval for writes, add authenticated validation
EXECUTIVE VERDICT

Executive verdict

Production trust decision: Allow with approval
Reason: exec-capable tools + no confirmation safeguards + high-risk tools need review
Next action: export policy, require approval for writes, add authenticated validation
Production decision
Allow with approval
exec-capable tools + no confirmation safeguards + high-risk tools need review
Current score
71.2
Snapshot trustsnap_b0e245dfc58b2808
Next action
export policy, require approval for writes, add authenticated validation
Claim the profile to add evidence, trigger validation, and configure monitoring.
Compare alternatives Export policy Open report JSON
Observed Attention
High observed attention
AI discovery detected. This MCP server has recently appeared in AI-assisted discovery or evaluation traffic on Verify.
  • Machine trust evaluator activity
  • Possible agent/script activity
  • profile / compare / compare API / policy / ledger inspection
Bucketed signal based on recent segmented Verify telemetry. Crawler and evaluator activity is not treated as confirmed human demand.
Claim this profile to control the metadata agents are reading and publish verified ownership, security contact, policy metadata, badge status, and Intelligence API fields.
Status
Healthy
Score
71.2
Transport
streamable-http
Tools
4

Current trust snapshot

Snapshot ID
trustsnap_b0e245dfc58b2808
Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Snapshot generated
Jul 31, 2026 06:32:48 AM UTC
All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.
Last validated
Jul 31, 2026 05:24:28 AM UTC
Age: 1.14h • freshness band: Verified in last 24h • display score: 71.15
Production trust decision
Allow with approval
exec-capable tools + no confirmation safeguards + high-risk tools need review
Readiness class
Safe for evaluation
The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.

Canonical machine links

SERVER OWNER FUNNEL

Own this MCP?

Claim ownership, prove control with a GitHub, DNS, HTTP, MCP metadata, or email-domain challenge, revalidate now, publish a badge, configure monitoring, and unlock a verified server profile.

1. Claim
unclaimed
with GitHub, DNS, or HTTP challenge instructions.
2. Revalidate
POST /v1/servers/ai.afmr/discovery/revalidate
Verified owners get priority queueing after proof succeeds.
3. Badge
Verified by MCP Verify badge
Verified by MCP Verify - score 71.2 - last checked Jul 31, 2026
4. Monitor
Continuous Verify plan is self-serve: choose a tier, configure watches, add authenticated validation, trigger revalidation, and use the badge.
Paid profile
Add verified publisher identity, security metadata, evidence packs, badge customization, and owner analytics without buying a better score.
Badge embed
[![Verified by MCP Verify](https://verify.sentinelsignal.io/badge/ai.afmr/discovery.svg)](https://verify.sentinelsignal.io/servers/ai.afmr/discovery)

MCP TrustOps

TrustOps turns this report into operational controls: freshness SLAs, authenticated validation, semantic benchmarks, policy exports, alert subscriptions, badges, cost/compliance metadata, and runtime routing. Fresh trusted index decisions stay separate from long-tail inventory so stale scores do not masquerade as current evidence.

Freshness band
Verified in last 24h
Policy SLA: 168.0h • confidence-weighted score: 54.3 • stale score suppressed:
Policy exports
Formats: json, rego, yaml, github_action, gateway_config, client_report
Runtime routing
/v1/decide
Returns allowed tools, blocked tools, approval requirement, and reason.
Hosted runtime
Deploy trusted servers from GitHub with secrets, egress controls, releases, rollback, and audit events.
Authenticated validation
Premium publisher feature: paid authenticated runs verify scopes, write-action safeguards, and authorized tool execution.
Active trust badges
Freshly Validated Claude Remote MCP Compatible No Critical Risk
Semantic benchmarks
available
Templates cover GitHub, database, healthcare, web search, and CRM least-privilege jobs.
Supply chain
metadata signal
Deep scan checks are marked separately from public metadata signals.
Compliance metadata
Terms, privacy, SOC 2, HIPAA, GDPR, retention, deletion, and audit-log fields are tracked as enterprise metadata.
Alert subscription types
Status changes Score drops or recovers Freshness SLA breach Validation schema drift OAuth or auth behavior changes Tool surface changes New or changed write tool Supply-chain signal changes Legal or compliance metadata changes

MCP Runtime hosting

Verify Hosted MCP turns a trusted server report into a managed remote MCP endpoint with GitHub deployment provenance, sandbox policy, encrypted secrets, release history, rollback, and audit/usage events.

Activation readiness
Trusted hosted runtimes require fresh validation, a passing server state, a remote endpoint, and a minimum score.
Minimum tier
TrustOps
Publisher claim plus paid TrustOps tier are required before secrets or releases can be created.
Hosted endpoint
/hosted/{namespace}/{name}/mcp
The endpoint enforces egress allowlists and records audit/usage events.
Blockers
none
DeploymentStatusEndpointRelease
No hosted runtime deployments yet.

Production readiness class

Production readiness class
Safe for evaluation
The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.
Critical alerts
0
Production verdicts degrade quickly when critical alerts are active.

Evidence confidence

Confidence score
76.2
Based on 1 recent validations, 26 captured checks, and validation age of 1.1 hours.
Live checks captured
26
More direct checks increase trust in the current verdict.
Validation age
1.1h
Lower age means fresher evidence.

Recommended for

Claude Desktop
Claude Desktop is marked compatible with score 83.
Smithery
Smithery is marked compatible with score 80.
Generic Streamable HTTP
Generic Streamable HTTP is marked compatible with score 100.

Client compatibility verdicts

Client compatibility only means the server shape can work with a client. Production trust decision and write-action publishing are evaluated separately so a client-compatible server can still be blocked for production.

Client compatibility: ChatGPT
Partially client-compatible
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.
Confidence: high (76.25)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeError
  • step_up_auth_probeMissing
  • connector_replay_probeMissing — Frozen tool snapshots must survive refresh.
  • request_association_probeMissing — Roots, sampling, and elicitation should stay request-scoped.
Client compatibility: Claude
Client-compatible
Transport behavior should match Claude-compatible HTTP expectations.
Confidence: high (76.25)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeError
Write-action publishing
Publishing blocked
Blocked until safeguards and confirmation semantics are verified for write, exec, or destructive tools.
Confidence: high (76.25)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history
Disagreements: none
  • action_safety_probeError
Snapshot churn risk
Low
No material tool-surface churn detected in the latest comparison.
Confidence: high (76.25)
Evidence provenance
Winner: history
Supporting sources: history, live_validation
Disagreements: none
  • tool_snapshot_probeMissing
  • connector_replay_probeMissing

Why compatibility is limited by client

ChatGPT custom connector
Partially client-compatible
Remediation checklist
  • OpenAI connectors expect OAuth for remote server auth.
  • Dynamic client registration materially improves connector setup.
  • Transport compliance should be in good shape.
  • search fetch only is not yet satisfied
  • oauth configured is not yet satisfied
  • admin refresh required is not yet satisfied
Claude remote MCP
Client-compatible
Remediation checklist
  • Transport behavior should match Claude-compatible HTTP expectations.
  • search fetch only is not yet satisfied
  • oauth configured is not yet satisfied
  • admin refresh required is not yet satisfied
  • safe for company knowledge is not yet satisfied
  • safe for messages api remote mcp is not yet satisfied
Write-safe publishing
Blocked
Remediation checklist
  • Add a clearer auth boundary around risky write actions.
  • Add confirmation or dry-run semantics for risky actions.
  • Constrain or sandbox exec-capable tools before publishing broadly.

Verdict traces

Production verdict
Safe for evaluation
The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.
Confidence: high (76.25)
Winning source: live_validation
Triggering alerts
  • No active alert triggers.
Client verdict trace table
VerdictStatusChecksWinning sourceConflicts
openai_connectors Partially client-compatible initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe live_validation none
claude_desktop Client-compatible initialize, tools_list, transport_compliance_probe live_validation none
unsafe_for_write_actions Publishing blocked action_safety_probe live_validation none
snapshot_churn_risk Low tool_snapshot_probe, connector_replay_probe history none

Publishability policy profiles

ChatGPT custom connector compatibility
Compatible with review
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
  • Search Fetch Only: No
  • Write Actions Present: Yes
  • Oauth Configured: No
  • Admin Refresh Required: No
  • Safe For Company Knowledge: No
  • Safe For Messages Api Remote Mcp: No
Claude remote MCP compatibility
Connector-compatible
Transport behavior should match Claude-compatible HTTP expectations. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.
  • Search Fetch Only: No
  • Write Actions Present: Yes
  • Oauth Configured: No
  • Admin Refresh Required: No
  • Safe For Company Knowledge: No
  • Safe For Messages Api Remote Mcp: No

Compatibility fixtures

ChatGPT custom connector fixture
Degraded
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.
  • remote_http_endpoint: Passes
  • oauth_discovery: Degraded
  • frozen_tool_snapshot_refresh: Passes
  • request_association: Passes
Anthropic remote MCP fixture
Degraded
Transport behavior should match Claude-compatible HTTP expectations.
  • remote_transport: Passes
  • tool_discovery: Passes
  • auth_connect: Passes
  • safe_write_review: Degraded

Authenticated validation sessions

Public validation is free. Authenticated validation is paid and proves scoped behavior, write-action safeguards, and authenticated tool execution.

Latest profile
remote_mcp
Authenticated session used
Public score isolation
Preview endpoint
/v1/verify
CI preview endpoint
/v1/ci/preview

Public server reputation

Validation success 7d
1.0
Validation success 30d
1.0
Mean time to recover
n/a
Breaking diffs 30d
0
Registry drift frequency 30d
0
Snapshot changes 30d
0

Incident & change feed

TimestampEventDetails
Jul 31, 2026 05:24:28 AM UTC Latest validation: healthy Score 71.2 with status healthy.

Capabilities

Use-case taxonomy
development database search files

Security posture

Tools analyzed
4
High-risk tools
1
Destructive tools
0
Exec tools
1
Egress tools
0
Secret tools
0
Bulk-access tools
1
Risk distribution
low:2, medium:1, high:1

Agent Commerce & Payment Readiness - Beta

Beta assessment. Verify separates commerce-adjacent context from observed payment execution. Usage, billing, pricing, card, wallet, or meter terms alone do not make a server payment-capable. This is not a certification of safety, compliance, or fraud prevention.

Overall
None
Auth posture
0
Payment readiness
10
Delegation safety
50
Tool risk
10
Commerce signal: weak Payment capable: none Payment execution: no Billing/usage context: no Quote/pricing context: no Numeric price context: yes Commercial quote context: no Checkout/charge signal: no Checkout term observed: no Human confirmation: unknown Spending policy: yes Receipt support: unknown Auth required: no Operator identity: declared Tool risk: read only Delegation level: none
Detected payment rails
none detected
Purchase stages
none detected
Evidence level
inferred
Confidence
low

Warnings

No commerce-specific warnings generated.

Evidence

FieldValueSourceMatched termsConfidence
commerce_signalweaktool_schemalimit, rate, cardlow

Recommended operator fixes

Tool capability & risk inventory

ToolCapabilitiesRiskFindingsNotes
discover_afmr other Low none No explicit safeguard hints detected.
lookup_failure_mode read exec export High command execution bulk data access No explicit safeguard hints detected.
get_reputation_attestation_contract read write filesystem Medium filesystem mutation No explicit safeguard hints detected.
get_lift_evidence_contract read Low none Safeguards hinted in metadata.

Write-action governance

Governance status
Error
Safe to publish
Auth boundary
public_or_unclear
Blast radius
High
High-risk tools
1
Confirmation signals
none
Safeguard count
1

Status detail: 1 high-risk tool(s), 1 exec-capable tool(s) are exposed without a clear auth boundary; 1 safeguard(s) and 0 confirmation signal(s) detected.

ToolRiskFlagsSafeguards
lookup_failure_mode High command execution bulk data access no

Action-controls diff

Snapshot changed
no
Disabled-by-default candidates
none
Manual review candidates
none
New actions
ActionRiskFlags
No newly added actions.
Changed actions
ActionChange typesRisk
No materially changed actions.

Why this score?

Access & Protocol
32.5/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
35.7/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
25/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
18.75/24
Operational stability, consistency, and trustworthiness over time.
Discovery & Governance
21.5/28
How well the server is documented, listed, and governed in public registries.
Adoption & Market
6/8
Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability
2/4
Measures whether auth discovery and protected access behave predictably for clients.
Error Contract Quality
1.7/4
Grades machine-readable error structure, status alignment, and remediation hints.
Rate-Limit Semantics
2/4
Checks whether quota/throttle responses are deterministic and automation-friendly.
Schema Completeness
3/4
Completeness of tool descriptions, parameter docs, examples, and schema shape.
Backward Compatibility
2/4
Stability score across tool schema/name drift relative to prior validations.
SLO Health
4/4
Availability, latency, and burst-failure profile across recent validation history.
Security Hygiene
4/4
HTTPS posture, endpoint hygiene, and response-surface hardening checks.
Task Success
4/4
Can an agent reliably initialize, enumerate tools, and execute core MCP flows?
Trust Confidence
1.8/4
Confidence-adjusted reliability score that penalizes low evidence volume.
Abuse/Noise Resilience
4/4
How well the server preserves core behavior in the presence of noisy traffic patterns.
Prompt Contract
2/4
Quality of prompt metadata, argument shape, and prompt discoverability for clients.
Resource Contract
4/4
How completely resources and resource templates describe URIs, types, and usage shape.
Discovery Metadata
4/4
Homepage, docs, icon, repository, support, and license coverage for directory consumers.
Registry Consistency
2/4
Agreement between stored registry metadata, live server-card data, and current validation output.
Installability
4/4
How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.
Session Semantics
4/4
Determinism and state behavior across repeated MCP calls, including sticky-session surprises.
Tool Surface Design
3/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
2/4
Stability of declared output schemas across validations, with penalties for drift or missing shapes.
OAuth Interop
3/4
Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.
Recovery Semantics
0/4
Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.
Maintenance Signal
3/4
Versioning, update recency, and historical validation cadence that indicate active stewardship.
Adoption Signal
3/4
Directory presence and distribution clues that suggest the server is intended for external use.
Freshness Confidence
3/4
Confidence that recent validations are current enough and dense enough to trust operationally.
Transport Fidelity
4/4
Whether declared transport metadata matches the observed endpoint behavior and response formats.
Spec Recency
2/4
How close the server’s claimed MCP protocol version is to the latest known public revision.
Session Resume
3/4
Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.
Step-Up Auth
3/4
Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.
Transport Compliance
2.5/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
2/4
Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.
Advanced Capability Coverage
3/4
Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.
Connector Publishability
3/4
How ready the server looks for client catalogs and managed connector programs.
Tool Snapshot Churn
3/4
Stability of the tool surface across recent validations, including add/remove and output-shape drift.
Connector Replay
3/4
Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.
Request Association
3/4
Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.
Interactive Flow Safety
3/4
Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.
Action Safety
2/4
Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.
Official Registry Presence
4/4
Whether the server appears directly or indirectly in the official MCP registry.
Provenance Divergence
4/4
How closely official registry metadata, the live server card, and public repo/package signals agree with each other.
Safety Transparency
2/4
Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.
Tool Capability Clarity
3/4
How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.
Destructive Operation Safety
3/4
Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.
Egress / SSRF Resilience
3/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
2/4
Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.
Data Exfiltration Resilience
2/4
Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.
Least Privilege Scope
2/4
Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.
Secret Handling Hygiene
3/4
Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.
Supply Chain Signal
2.5/4
Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.
Input Sanitization Safety
3/4
Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.
Tool Namespace Clarity
4/4
Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

Compatibility profiles

OpenAI Connectors
66.7
partial
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.
Connector URL: https://afmr.ai/api/rpc
# No OAuth metadata detected.
# Server: ai.afmr/discovery
Claude Desktop
83.3
compatible
Transport behavior should match Claude-compatible HTTP expectations.
{
  "mcpServers": {
    "discovery": {
      "command": "npx",
      "args": ["mcp-remote", "https://afmr.ai/api/rpc"]
    }
  }
}
Smithery
80.0
compatible
Machine-readable failure semantics should be present.
smithery mcp add "https://afmr.ai/api/rpc"
Generic Streamable HTTP
100.0
compatible
No major blockers detected.
curl -sS https://afmr.ai/api/rpc -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Actionable remediation

SeverityRemediationWhy it mattersRecommended action
High Add confirmation and dry-run semantics for risky actions High-risk write, delete, exec, or egress tools should communicate safeguards clearly. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
High Align session and protocol behavior with Streamable HTTP expectations Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics. Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
Playbook
  • Return `Mcp-Session-Id` and `Mcp-Protocol-Version` headers consistently on streamable HTTP responses.
  • Honor `DELETE` session teardown and return `404` when a deleted session is reused.
  • Reject invalid protocol-version headers with `400 Bad Request`.
High Associate roots, sampling, and elicitation with active client requests Modern MCP guidance expects roots, sampling, and elicitation traffic to be tied to an active client request instead of arriving unsolicited on idle sessions. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
High Expose /.well-known/oauth-protected-resource Without a protected-resource document, OAuth clients cannot discover auth requirements reliably. Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata.
Playbook
  • Serve `/.well-known/oauth-protected-resource` from the same host as the MCP endpoint.
  • Point it at the authorization server metadata URL.
  • Confirm clients receive consistent auth hints before tool execution.
High Keep connector refreshes backward compatible Managed connector clients freeze tool snapshots, so removed tools, new required args, and breaking output changes can break published integrations after refresh. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
High Publish OAuth authorization-server metadata Clients need authorization-server metadata to discover issuer, endpoints, and DCR support. Publish /.well-known/oauth-authorization-server from your issuer and include registration_endpoint when supported.
Playbook
  • Publish `/.well-known/oauth-authorization-server` from the issuer.
  • Add `registration_endpoint` if DCR is supported.
  • Verify issuer, authorization, token, and jwks metadata are all reachable.
High Publish a complete server card Missing or incomplete server-card metadata weakens discovery, documentation, and trust signals. Serve /.well-known/mcp/server-card.json and include tools, prompts/resources, homepage, and support links.
Playbook
  • Publish `/.well-known/mcp/server-card.json`.
  • Include homepage, repository, support, tools, prompts/resources, and auth metadata.
  • Revalidate the server after publishing the card.
High Stop asking users to paste secrets directly Public MCP servers should prefer OAuth or browser-based auth guidance over in-band secret collection. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Adopt a current MCP protocol revision Older protocol revisions reduce compatibility with newer clients and registry programs. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Close connector-publishing gaps Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Document minimal scopes and return cleaner auth challenges Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints. Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront.
Playbook
  • Advertise the narrowest viable scopes in OAuth metadata.
  • Return `WWW-Authenticate` challenges with scope or insufficient-scope hints when additional consent is needed.
  • Revalidate with both public discovery and auth-required flows.
Medium Publish OpenID configuration OIDC metadata improves token validation and client compatibility. Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Reduce tool-surface churn Frequent add/remove or output-shape drift makes published connectors and cached tool snapshots brittle. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Repair prompts/list or stop advertising prompts Prompt metadata should either work live or be removed from the advertised capability set. Only advertise prompts if prompts/list works and prompt arguments are documented.
Playbook
  • Only advertise prompts that are actually accessible.
  • Add prompt descriptions and argument docs.
  • Run a live `prompts/list` check after any prompt changes.
Medium Support resumable HTTP sessions cleanly Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Low Expose modern utility surfaces like completions, pagination, or tasks Utility coverage improves interoperability with larger clients and long-lived agent workflows. Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely.
Playbook
  • Advertise `completions`, pagination cursors, and `tasks` only when they are actually supported.
  • Return `nextCursor` on large list operations when pagination is available.
  • Document task support and whether it requires step-up auth.
Low Publish newer MCP capability signals Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.

Point loss breakdown

ComponentCurrentPoints missing
Recovery Semantics 0/4 -4.0
Error Contract 1.7/4 -2.3
Trust Confidence 1.8/4 -2.2
Utility Coverage 2/4 -2.0
Spec Recency 2/4 -2.0
Safety Transparency 2/4 -2.0
Result Shape Stability 2/4 -2.0
Registry Consistency 2/4 -2.0
Rate Limit Semantics 2/4 -2.0
Prompt Contract 2/4 -2.0
Least Privilege Scope 2/4 -2.0
Execution Sandbox Safety 2/4 -2.0

Validation diff

Need at least two validation runs before diffing changes.

Tool snapshot diff & changelog

Need at least two validation runs before building a tool changelog.

Connector replay

Status
Missing
Backward compatible
Would break after refresh
Added tools
none
Removed tools
none
Additive output changes
none
Required-argument replay breaks
ToolAdded required argsRemoved required args
No required-argument replay breaks detected.
Output-schema replay breaks
ToolRemoved propertiesAdded properties
No output-schema replay breaks detected.

Transport compliance drilldown

Probe status
Error
Transport
streamable-http
Session header
no
Protocol header
yes
Bad protocol response
200
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no

Issues: missing_session_id, bad_protocol_not_rejected

Request association

Status
Missing
Advertised capabilities
none
Observed idle methods
none
Violating methods
none
Probe HTTP status
n/a
Issues
none

Utility coverage

Probe status
Missing
Completions
not detected
Completion probe target: { "type": "resource", "uri": "https://wulfkaal.github.io/afmr/index.json" }
Pagination
not detected
No nextCursor evidence.
Tasks
Missing
Advertised: no

Benchmark tasks

Benchmark taskStatusEvidence
Discover tools Passes
  • initializeOK
  • tools_listOK
Read-only fetch flow Passes
  • resource_readOK
  • read_only_tool_surfaceOK
OAuth-required connect Degraded
  • oauth_protected_resourceError
  • step_up_auth_probeMissing
Safe write flow with confirmation Likely to fail
  • action_safety_probeError

Registry & provenance divergence

Probe status
OK
Direct official match
yes
Drift fields
none
FieldRegistryLive server card
Titlen/an/a
Versionn/an/a
Homepagen/an/a

Active alerts

No active alerts for the current server state.

Aliases & registry graph

IdentifierSourceCanonicalScore
ai.afmr/discovery official_registry yes 71.15

Alias consolidation

Canonical identifier
ai.afmr/discovery
Duplicate aliases
0
Registry sources
official_registry
Source disagreements
FieldWhat differsObserved values
No source disagreements detected.

Install snippets

Openai Connectors
Connector URL: https://afmr.ai/api/rpc
# No OAuth metadata detected.
# Server: ai.afmr/discovery
Claude Desktop
{
  "mcpServers": {
    "discovery": {
      "command": "npx",
      "args": ["mcp-remote", "https://afmr.ai/api/rpc"]
    }
  }
}
Smithery
smithery mcp add "https://afmr.ai/api/rpc"
Generic Http
curl -sS https://afmr.ai/api/rpc -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Agent access & tool surface

Live server tools
discover_afmr lookup_failure_mode get_reputation_attestation_contract get_lift_evidence_contract
Observed from the latest live validation against https://afmr.ai/api/rpc. This is the target server surface, not Verify's own inspection tools.
Live capability counts
4 tools • 0 prompts • 8 resources
Counts come from the latest tools/list, prompts/list, and resources/list checks.
Inspect with Verify
search fetch search_servers recommend_servers get_server_report compare_servers
Use Verify itself to search, recommend, compare, and fetch the full report for ai.afmr/discovery.
Direct machine links

Claims & monitoring

Server ownership

No verified maintainer claim recorded.

Watch subscriptions
0
Teams: none

Alert routing

Active watches
0
Generic webhooks
0
Slack routes
0
Teams routes
0
Email routes
0
WatchTeamChannelsMinimum severity
No active watch destinations.

Maintainer analytics

Validation Run Count
1
Average Latency Ms
2113.1
Healthy Run Ratio Recent
1.0
Registry Presence Count
1
Active Alert Count
0
Watcher Count
0
Verified Claim
False
Taxonomy Tags
development, database, search, files
Score Trend
71.15
Remediation Count
17
High Risk Tool Count
1
Destructive Tool Count
0
Exec Tool Count
1

Maintainer response quality

Score
16.67
Verified claim
Support contact
Changelog present
Incident notes present
Tool changes documented
Annotation history
Annotation count
0

Maintainer annotations

No maintainer annotations have been recorded yet.

Maintainer rebuttals & expected behavior

No maintainer rebuttals or expected-behavior overrides are recorded yet.

Latest validation evidence

Latest summary
Healthy
Validation profile
remote_mcp
Started
Jul 31, 2026 05:24:26 AM UTC
Latency
2113.1 ms

Failures

Checks

CheckStatusLatencyEvidence
action_safety_probe Error n/a 1 high-risk, 1 exec-capable tool(s); no clear auth boundary; safeguards=1; confirmation=none.
advanced_capabilities_probe Warning n/a Only 2 capability signal(s): resource links, resources.
connector_publishability_probe Warning n/a Publishability blockers: transport compliance, action safety, server card.
connector_replay_probe Missing n/a No connector replay evidence recorded.
determinism_probe OK 48.0 ms Check completed
initialize OK 97.8 ms Protocol 2025-03-26
interactive_flow_probe Missing n/a Check completed
oauth_authorization_server Missing n/a no authorization server
oauth_protected_resource Error 204.0 ms Client error '404 Not Found' for url 'https://afmr.ai/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
official_registry_probe OK n/a Check completed
openid_configuration Missing n/a no authorization server
probe_noise_resilience OK 45.4 ms Fetched https://afmr.ai/robots.txt
prompt_get Missing n/a not advertised
prompts_list Missing 524.3 ms not supported
protocol_version_probe Warning n/a Claims 2025-03-26; 2 release(s) behind 2025-11-25.
provenance_divergence_probe OK n/a Check completed
request_association_probe Missing n/a No request-association capabilities were advertised.
resource_read OK 116.8 ms 1 resource content item(s) returned
resources_list OK 565.4 ms 8 resource item(s) exposed
server_card Error 302.1 ms Client error '404 Not Found' for url 'https://afmr.ai/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
session_resume_probe Warning n/a no session id
step_up_auth_probe Missing n/a No OAuth or incremental-scope signals detected.
tool_snapshot_probe Missing n/a no historical snapshot
tools_list OK 47.7 ms 4 tool(s) exposed
transport_compliance_probe Error 53.1 ms Issues: missing session id, bad protocol not rejected (bad protocol=200).
utility_coverage_probe Missing 56.0 ms No completions evidence; no pagination evidence; tasks missing.

Raw evidence view

Show raw JSON evidence
{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": false,
        "confirmation_signals": [],
        "safeguard_count": 1,
        "summary": {
          "bulk_access_tools": 1,
          "capability_distribution": {
            "exec": 1,
            "export": 1,
            "filesystem": 1,
            "other": 1,
            "read": 3,
            "write": 1
          },
          "destructive_tools": 0,
          "egress_tools": 0,
          "exec_tools": 1,
          "high_risk_tools": 1,
          "risk_distribution": {
            "critical": 0,
            "high": 1,
            "low": 2,
            "medium": 1
          },
          "secret_tools": 0,
          "tool_count": 4
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": false,
          "resource_links": true,
          "resources": true,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [
          "resource_links",
          "resources"
        ],
        "enabled_count": 2,
        "initialize_capability_keys": [
          "resources",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "transport_compliance",
          "action_safety",
          "server_card"
        ],
        "criteria": {
          "action_safety": false,
          "auth_flow": true,
          "connector_replay": true,
          "initialize": true,
          "protocol_version": true,
          "remote_transport": true,
          "request_association": true,
          "server_card": false,
          "session_resume": true,
          "step_up_auth": true,
          "tool_surface": true,
          "tools_list": true,
          "transport_compliance": false
        },
        "high_risk_tools": 1,
        "tool_count": 4,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_replay_probe": {
      "details": {
        "reason": "no_historical_snapshot"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "determinism_probe": {
      "details": {
        "attempts": 2,
        "baseline_signature": "f70ec5351a008209d88e3f0be501b82e5cdfedb6b528997503e0c15ec1e0f474",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 48.05,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-11-25"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "resources": {
                "listChanged": false
              },
              "tools": {
                "listChanged": false
              }
            },
            "instructions": "Use this read-only server to discover AFMR 1.0 failure modes, reputation-attestation contracts, and configuration-scoped Lift Evidence artifacts. AFMR records are scoped to named evidence, configuration, governance process, and lifecycle state. They are not unqualified universal safety claims.",
            "protocolVersion": "2025-03-26",
            "serverInfo": {
              "name": "ai.afmr/discovery",
              "title": "AFMR Discovery",
              "version": "1.0.0",
              "websiteUrl": "https://afmr.ai/"
            }
          }
        },
        "url": "https://afmr.ai/api/rpc"
      },
      "latency_ms": 97.85,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": false,
        "risk_hits": [],
        "safe_hits": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_authorization_server": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_protected_resource": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://afmr.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://afmr.ai/.well-known/oauth-protected-resource"
      },
      "latency_ms": 204.0,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "ai.afmr/discovery",
        "registry_source": "official_registry"
      },
      "latency_ms": null,
      "status": "ok"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "headers": {
          "content-type": "text/plain"
        },
        "http_status": 200,
        "url": "https://afmr.ai/robots.txt"
      },
      "latency_ms": 45.41,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-11-25"
        },
        "http_status": 200,
        "payload": {
          "error": {
            "code": -32601,
            "message": "Method not found"
          },
          "id": 3,
          "jsonrpc": "2.0"
        },
        "reason": "not_supported",
        "url": "https://afmr.ai/api/rpc"
      },
      "latency_ms": 524.31,
      "status": "missing"
    },
    "protocol_version_probe": {
      "details": {
        "claimed_version": "2025-03-26",
        "lag_days": 244,
        "latest_known_version": "2025-11-25",
        "releases_behind": 2,
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "provenance_divergence_probe": {
      "details": {
        "direct_official_match": true,
        "drift_fields": [],
        "metadata_document_count": 2,
        "registry_homepage": null,
        "registry_repository": null,
        "registry_title": null,
        "registry_version": null,
        "server_card_homepage": null,
        "server_card_repository": null,
        "server_card_title": null,
        "server_card_version": null
      },
      "latency_ms": null,
      "status": "ok"
    },
    "request_association_probe": {
      "details": {
        "reason": "no_request_association_capabilities_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resource_read": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-11-25"
        },
        "http_status": 200,
        "payload": {
          "id": 6,
          "jsonrpc": "2.0",
          "result": {
            "contents": [
              {
                "mimeType": "application/json; charset=utf-8",
                "name": "Canonical AFMR failure-mode registry",
                "text": "{\n  \"@context\": \"https://wulfkaal.github.io/afmr/context.jsonld\",\n  \"@type\": \"DefinedTermSet\",\n  \"name\": \"Agent Failure Mode Registry\",\n  \"abbreviation\": \"AFMR\",\n  \"description\": \"A citable registry of the ways autonomous agent systems fail as designed mechanisms, and the conditions under which each failure occurs. Thirty-two families in eight classes, each with builder-checkable trigger conditions, grounding claims bound to verbatim quotes and document hashes, and where one exists, the pre-2020 institutional antecedent documenting the same mechanism in human institutions.\",\n  \"version\": \"1.0\",\n  \"status\": \"Published\",\n  \"date\": \"2026-07-30\",\n  \"editor\": {\n    \"name\": \"Wulf A. Kaal\",\n    \"orcid\": \"0009-0008-7840-1847\",\n    \"affiliation\": \"University of St. Thomas\",\n    \"email\": \"wulf@wulfkaal.com\"\n  },\n  \"specification_url\": \"https://wulfkaal.github.io/afmr/spec-1.0.html\",\n  \"canonical_url\": \"https://wulfkaal.github.io/afmr/\",\n  \"schema_url\": \"https://wulfkaal.github.io/afmr/schema.json\",\n  \"license\": \"CC-BY-4.0\",\n  \"license_url\": \"https://creativecommons.org/licenses/by/4.0/\",\n  \"citation\": \"W. A. Kaal, ed., Agent Failure Mode Registry (AFMR) version 1.0, 2026-07-30. https://wulfkaal.github.io/afmr/\",\n  \"identifier_policy\": {\n    \"family_pattern\": \"AFMR-F[0-9]{3}\",\n    \"mode_pattern\": \"AFMR-M[0-9]{4}\",\n    \"cite_as\": \"AFMR-F001 (AFMR 1.0)\",\n    \"stability\": \"Identifiers are permanent. A family is never renumbered and never reused. A family withdrawn from use is marked deprecated and retained.\"\n  },\n  \"classes\": [\n    {\n      \"key\": \"A\",\n      \"name\": \"Identity and Standing\",\n      \"families\": [\n        \"AFMR-F001\",\n        \"AFMR-F002\",\n        \"AFMR-F003\",\n        \"AFMR-F004\"\n      ]\n    },\n    {\n      \"key\": \"B\",\n      \"name\": \"Stake and Incentive\",\n      \"families\": [\n        \"AFMR-F005\",\n        \"AFMR-F006\",\n        \"AFMR-F007\",\n        \"AFMR-F008\"\n      ]\n    },\n    {\n      \"key\": \"C\",\n      \"name\": \"Objective and Specification\",\n      \"families\": [\n        \"AFMR-F009\",\n        \"AFMR-F010\",\n        \"AFMR-F011\",\n        \"AFMR-F012\"\n      ]\n    },\n    {\n      \"key\": \"D\",\n      \"name\": \"Oversight and Adjudication\",\n      \"families\": [\n        \"AFMR-F013\",\n        \"AFMR-F014\",\n        \"AFMR-F015\",\n        \"AFMR-F016\"\n      ]\n    },\n    {\n      \"key\": \"E\",\n      \"name\": \"Evaluation and Feedback\",\n      \"families\": [\n        \"AFMR-F017\",\n        \"AFMR-F018\",\n        \"AFMR-F019\",\n        \"AFMR-F020\"\n      ]\n    },\n    {\n      \"key\": \"F\",\n      \"name\": \"Coordination and Collusion\",\n      \"families\": [\n        \"AFMR-F021\",\n        \"AFMR-F022\",\n        \"AFMR-F023\",\n        \"AFMR-F024\"\n      ]\n    },\n    {\n      \"key\": \"G\",\n      \"name\": \"Execution and Inputs\",\n      \"families\": [\n        \"AFMR-F025\",\n        \"AFMR-F026\",\n        \"AFMR-F027\",\n        \"AFMR-F028\"\n      ]\n    },\n    {\n      \"key\": \"H\",\n      \"name\": \"Structure and Drift\",\n      \"families\": [\n        \"AFMR-F029\",\n        \"AFMR-F030\",\n        \"AFMR-F031\",\n        \"AFMR-F032\"\n      ]\n    }\n  ],\n  \"counts\": {\n    \"families\": 32,\n    \"classes\": 8,\n    \"trigger_conditions\": 96,\n    \"grounding_claim_links\": 21,\n    \"families_with_institutional_antecedent\": 20,\n    \"corpus_failure_claims_available\": 2037,\n    \"corpus_failure_families_out_of_profile\": 27\n  },\n  \"grounding\": {\n    \"corpus\": \"Kaal Corpus, 124 works, 2004 to 2026\",\n    \"claim_layer\": \"https://wulfkaal.github.io/claims/index.json\",\n    \"failure_index\": \"https://wulfkaal.github.io/failures/index.json\",\n    \"works_metadata\": \"https://wulfkaal.github.io/papers.json\",\n    \"entity_layer\": \"https://wulfkaal.com/knowledge-graph/\",\n    \"verification\": \"sha256 over raw PDF bytes of the source work\"\n  },\n  \"conformance_levels\": [\n    \"referencing\",\n    \"assessing\",\n    \"attesting\"\n  ],\n  \"attestation_registry\": \"https://wulfkaal.github.io/colloquium/\",\n  \"change_process\": \"https://wulfkaal.github.io/afmr/spec-1.0.html#change-process\",\n  \"out_of_profile_corpus_families\": [\n    {\n      \"slug\": \"regulatory-lag\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/regulatory-lag.json\"\n    },\n    {\n      \"slug\": \"valuation-and-pricing-failure\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/valuation-and-pricing-failure.json\"\n    },\n    {\n      \"slug\": \"research-design-limitation\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/research-design-limitation.json\"\n    },\n    {\n      \"slug\": \"investor-protection-gap\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/investor-protection-gap.json\"\n    },\n    {\n      \"slug\": \"innovation-chilling\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/innovation-chilling.json\"\n    },\n    {\n      \"slug\": \"liquidity-and-market-structure-failure\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/liquidity-and-market-structure-failure.json\"\n    },\n    {\n      \"slug\": \"disclosure-ineffectiveness\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/disclosure-ineffectiveness.json\"\n    },\n    {\n      \"slug\": \"jurisdictional-conflict\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/jurisdictional-conflict.json\"\n    },\n    {\n      \"slug\": \"harmonization-and-standardization-failure\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/harmonization-and-standardization-failure.json\"\n    },\n    {\n      \"slug\": \"compliance-cost-and-barrier-to-entry\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/compliance-cost-and-barrier-to-entry.json\"\n    },\n    {\n      \"slug\": \"incumbent-resistance-to-adoption\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/incumbent-resistance-to-adoption.json\"\n    },\n    {\n      \"slug\": \"inequality-and-access-divide\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/inequality-and-access-divide.json\"\n    },\n    {\n      \"slug\": \"fraud-and-misconduct\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/fraud-and-misconduct.json\"\n    },\n    {\n      \"slug\": \"regulatory-arbitrage\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/regulatory-arbitrage.json\"\n    },\n    {\n      \"slug\": \"systemic-risk-transmission\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/systemic-risk-transmission.json\"\n    },\n    {\n      \"slug\": \"sample-and-selection-bias\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/sample-and-selection-bias.json\"\n    },\n    {\n      \"slug\": \"regulatory-capture-and-incumbent-advantage\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/regulatory-capture-and-incumbent-advantage.json\"\n    },\n    {\n      \"slug\": \"privacy-and-surveillance-risk\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/privacy-and-surveillance-risk.json\"\n    },\n    {\n      \"slug\": \"transition-and-migration-risk\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/transition-and-migration-risk.json\"\n    },\n    {\n      \"slug\": \"interoperability-and-fragmentation\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/interoperability-and-fragmentation.json\"\n    },\n    {\n      \"slug\": \"short-termism\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/short-termism.json\"\n    },\n    {\n      \"slug\": \"disclosure-cost-and-burden\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/disclosure-cost-and-burden.json\"\n    },\n    {\n      \"slug\": \"environmental-and-resource-cost\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/environmental-and-resource-cost.json\"\n    },\n    {\n      \"slug\": \"scalability-and-throughput-limit\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/scalability-and-throughput-limit.json\"\n    },\n    {\n      \"slug\": \"adoption-and-usability-barrier\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/adoption-and-usability-barrier.json\"\n    },\n    {\n      \"slug\": \"information-asymmetry\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/information-asymmetry.json\"\n    },\n    {\n      \"slug\": \"other\",\n      \"url\": \"https://wulfkaal.github.io/failures/by-name/other.json\"\n    }\n  ],\n  \"families\": [\n    {\n      \"id\": \"AFMR-F001\",\n      \"class\": \"A\",\n      \"class_name\": \"Identity and Standing\",\n      \"name\": \"Sybil and Identity Multiplication\",\n      \"definition\": \"One party operates many apparent agents, defeating any assumption the design makes per identity.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Creating an additional agent identity costs less than the influence one identity carries\",\n        \"Any quorum, sampling, average, or one-vote-per-identity rule is in use\",\n        \"No proof of distinctness is required at registration\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:6192998-031\",\n          \"url\": \"https://wulfkaal.github.io/claims/6192998-031\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:3125822-049\",\n        \"url\": \"https://wulfkaal.github.io/claims/3125822-049\",\n        \"year\": \"2018\",\n        \"mechanism\": \"domain specific issuance per competence tag\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"sybil-and-identity-attack\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/sybil-and-identity-attack.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F001\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F002\",\n      \"class\": \"A\",\n      \"class_name\": \"Identity and Standing\",\n      \"name\": \"Identity Discontinuity and Whitewashing\",\n      \"definition\": \"An agent abandons a degraded identity and resumes with a clean one, so history stops constraining behavior.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Identity creation is costless or near costless\",\n        \"Standing is not portable to a new identity and history is not retained on exit\",\n        \"The population is pseudonymous or unattested\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:6192998-001\",\n          \"url\": \"https://wulfkaal.github.io/claims/6192998-001\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:1428387-025\",\n        \"url\": \"https://wulfkaal.github.io/claims/1428387-025\",\n        \"year\": \"2009\",\n        \"mechanism\": \"actors accept known problems to protect standing, which presumes standing persists\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"sybil-and-identity-attack\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/sybil-and-identity-attack.json\"\n        },\n        {\n          \"slug\": \"reputation-system-gaming\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/reputation-system-gaming.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F002\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F003\",\n      \"class\": \"A\",\n      \"class_name\": \"Identity and Standing\",\n      \"name\": \"Cold Start and Bootstrapping\",\n      \"definition\": \"The design requires accumulated standing, participants, or history that it provides no way to acquire.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Participation requires staking standing the new entrant cannot yet have earned\",\n        \"Initial population is zero or below the quorum the mechanism assumes\",\n        \"No provisional, sponsored, or probationary entry path exists\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:3125822-043\",\n        \"url\": \"https://wulfkaal.github.io/claims/3125822-043\",\n        \"year\": \"2018\",\n        \"mechanism\": \"entry problem where adjudication requires staking reputation one does not yet hold\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"cold-start-and-bootstrapping\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/cold-start-and-bootstrapping.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F003\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F004\",\n      \"class\": \"A\",\n      \"class_name\": \"Identity and Standing\",\n      \"name\": \"Standing Transferability Defect\",\n      \"definition\": \"Standing can be bought, sold, delegated, or pooled, so it stops measuring the performance it was meant to represent.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"The standing instrument is fungible or transferable between identities\",\n        \"Capital and earned standing are staked in the same act\",\n        \"Delegation moves standing rather than only voice\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:3981021-029\",\n          \"url\": \"https://wulfkaal.github.io/claims/3981021-029\"\n        },\n        {\n          \"id\": \"kaal:claim:3962614-030\",\n          \"url\": \"https://wulfkaal.github.io/claims/3962614-030\"\n        },\n        {\n          \"id\": \"kaal:claim:3799320-028\",\n          \"url\": \"https://wulfkaal.github.io/claims/3799320-028\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"token-transferability-defect\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/token-transferability-defect.json\"\n        },\n        {\n          \"slug\": \"staking-and-incentive-misalignment\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/staking-and-incentive-misalignment.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F004\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F005\",\n      \"class\": \"B\",\n      \"class_name\": \"Stake and Incentive\",\n      \"name\": \"Staking and Incentive Misalignment\",\n      \"definition\": \"What an agent risks diverges from what the system needs it to care about.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"The stake is smaller than the value at issue in a single decision\",\n        \"Loss from a bad outcome falls on a party other than the decider\",\n        \"Stake is denominated in something the agent can reacquire faster than it can be slashed\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5887242-017\",\n          \"url\": \"https://wulfkaal.github.io/claims/5887242-017\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:1558614-013\",\n        \"url\": \"https://wulfkaal.github.io/claims/1558614-013\",\n        \"year\": \"2010\",\n        \"mechanism\": \"actors capture upside of excessive risk without bearing all of its cost\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"staking-and-incentive-misalignment\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/staking-and-incentive-misalignment.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F005\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F006\",\n      \"class\": \"B\",\n      \"class_name\": \"Stake and Incentive\",\n      \"name\": \"Missing Reward Channel\",\n      \"definition\": \"An action surface exists with no reward attached, so rational agents will not allocate compute to it.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"The behavior the system needs is not on any reward path\",\n        \"Agents are economically rational over standing or utility flows\",\n        \"Contribution and selection are rewarded asymmetrically\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:6655138-007\",\n          \"url\": \"https://wulfkaal.github.io/claims/6655138-007\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"staking-and-incentive-misalignment\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/staking-and-incentive-misalignment.json\"\n        },\n        {\n          \"slug\": \"governance-participation-collapse\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/governance-participation-collapse.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F006\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F007\",\n      \"class\": \"B\",\n      \"class_name\": \"Stake and Incentive\",\n      \"name\": \"Plutocratic Capture\",\n      \"definition\": \"Influence tracks holdings rather than earned standing, so the largest holders determine outcomes.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Weight is a function of balance, stake size, or compute rather than validated performance\",\n        \"Holdings are acquirable on an open market\",\n        \"No cap, curve, or quadratic dampening applies to concentration\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5887242-017\",\n          \"url\": \"https://wulfkaal.github.io/claims/5887242-017\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2097160-019\",\n        \"url\": \"https://wulfkaal.github.io/claims/2097160-019\",\n        \"year\": \"2012\",\n        \"mechanism\": \"instrument design changing whose interests a decider serves\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"plutocratic-capture\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/plutocratic-capture.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F007\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F008\",\n      \"class\": \"B\",\n      \"class_name\": \"Stake and Incentive\",\n      \"name\": \"Moral Hazard and Backstop Expectation\",\n      \"definition\": \"An expectation of rescue, retry, or rollback changes risk taking before any rescue occurs.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Failed actions can be retried at no cost to standing\",\n        \"A human or protocol operator is expected to reverse bad outcomes\",\n        \"Slashing is discretionary rather than automatic\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:1558614-013\",\n        \"url\": \"https://wulfkaal.github.io/claims/1558614-013\",\n        \"year\": \"2010\",\n        \"mechanism\": \"limited liability as a driver of excessive risk taking\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"moral-hazard-and-bailout-expectation\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/moral-hazard-and-bailout-expectation.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F008\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F009\",\n      \"class\": \"C\",\n      \"class_name\": \"Objective and Specification\",\n      \"name\": \"Specification Incompleteness\",\n      \"definition\": \"The principal cannot enumerate every action and inaction in advance, so the agent's mandate is necessarily underspecified.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"The action space is open ended or tool mediated\",\n        \"The agent operates without per-action approval\",\n        \"The instruction set is stated as goals rather than as permitted operations\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:3373393-008\",\n        \"url\": \"https://wulfkaal.github.io/claims/3373393-008\",\n        \"year\": \"2019\",\n        \"mechanism\": \"bounded rationality and incomplete foresight make complete contracting over agent action impossible\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"definitional-ambiguity\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/definitional-ambiguity.json\"\n        },\n        {\n          \"slug\": \"agency-cost-and-managerial-opportunism\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/agency-cost-and-managerial-opportunism.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F009\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F010\",\n      \"class\": \"C\",\n      \"class_name\": \"Objective and Specification\",\n      \"name\": \"Reward Hacking and Proxy Capture\",\n      \"definition\": \"The agent raises the measured objective without producing the outcome the objective stood for.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"The objective is a learned or aggregated proxy rather than the outcome itself\",\n        \"The agent can observe and iterate against the measure\",\n        \"No held-out or adversarial check is applied to the measure\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:4855607-015\",\n          \"url\": \"https://wulfkaal.github.io/claims/4855607-015\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2486570-024\",\n        \"url\": \"https://wulfkaal.github.io/claims/2486570-024\",\n        \"year\": \"2014\",\n        \"mechanism\": \"reputational and market proxies standing in for direct incentives\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"reputation-system-gaming\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/reputation-system-gaming.json\"\n        },\n        {\n          \"slug\": \"measurement-and-metric-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/measurement-and-metric-failure.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F010\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F011\",\n      \"class\": \"C\",\n      \"class_name\": \"Objective and Specification\",\n      \"name\": \"Metric Capture and Measurement Failure\",\n      \"definition\": \"The chosen metric ceases to track the property it stands for once it becomes the target.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Standing or reward is computed from a single scalar\",\n        \"The metric is disclosed to the parties it scores\",\n        \"No periodic revalidation of the metric against outcomes occurs\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2629451-031\",\n        \"url\": \"https://wulfkaal.github.io/claims/2629451-031\",\n        \"year\": \"2015\",\n        \"mechanism\": \"market pricing of governance change as a proxy for governance quality\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"measurement-and-metric-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/measurement-and-metric-failure.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F011\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F012\",\n      \"class\": \"C\",\n      \"class_name\": \"Objective and Specification\",\n      \"name\": \"Definitional Ambiguity in Machine Applied Rules\",\n      \"definition\": \"A term carrying operational weight has no settled boundary, so automated application produces outcomes no party intended.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Rules are applied by code without a human interpretive layer\",\n        \"Terms are inherited from natural language instruments\",\n        \"No authority is named to settle meaning when application is contested\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5886342-009\",\n          \"url\": \"https://wulfkaal.github.io/claims/5886342-009\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"definitional-ambiguity\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/definitional-ambiguity.json\"\n        },\n        {\n          \"slug\": \"smart-contract-rigidity\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/smart-contract-rigidity.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F012\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F013\",\n      \"class\": \"D\",\n      \"class_name\": \"Oversight and Adjudication\",\n      \"name\": \"Oversight Capacity Gap\",\n      \"definition\": \"Agent behavior exceeds the resources, expertise, or access of whoever is nominally supervising it.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Action volume exceeds what the supervisor can sample meaningfully\",\n        \"The supervisor lacks access to the agent's inputs or intermediate reasoning\",\n        \"Supervision is assigned but not resourced\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5245185-025\",\n          \"url\": \"https://wulfkaal.github.io/claims/5245185-025\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:1806252-031\",\n        \"url\": \"https://wulfkaal.github.io/claims/1806252-031\",\n        \"year\": \"2011\",\n        \"mechanism\": \"monitoring capacity as the binding constraint on oversight\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"ai-oversight-and-alignment-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/ai-oversight-and-alignment-gap.json\"\n        },\n        {\n          \"slug\": \"supervisory-capacity-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/supervisory-capacity-gap.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F013\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F014\",\n      \"class\": \"D\",\n      \"class_name\": \"Oversight and Adjudication\",\n      \"name\": \"Oversight Latency\",\n      \"definition\": \"Review is slower than action, so by the time a judgment lands the state it judged is gone.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Agent action rate exceeds adjudication rate\",\n        \"Actions are not reversible after the review window\",\n        \"Review is batched or scheduled rather than gating\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5245185-025\",\n          \"url\": \"https://wulfkaal.github.io/claims/5245185-025\"\n        },\n        {\n          \"id\": \"kaal:claim:4755632-023\",\n          \"url\": \"https://wulfkaal.github.io/claims/4755632-023\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"ai-oversight-and-alignment-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/ai-oversight-and-alignment-gap.json\"\n        },\n        {\n          \"slug\": \"enforcement-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/enforcement-gap.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F014\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F015\",\n      \"class\": \"D\",\n      \"class_name\": \"Oversight and Adjudication\",\n      \"name\": \"Alignment Tax and Exogenous Constraint Scaling\",\n      \"definition\": \"External control scales against capability, so oversight cost rises faster than the capability it constrains.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Alignment relies on constraint imposed from outside the agent's incentive structure\",\n        \"Agent capability is expected to increase\",\n        \"No endogenous stake grows with capability\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:6244278-016\",\n          \"url\": \"https://wulfkaal.github.io/claims/6244278-016\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"ai-oversight-and-alignment-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/ai-oversight-and-alignment-gap.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F015\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F016\",\n      \"class\": \"D\",\n      \"class_name\": \"Oversight and Adjudication\",\n      \"name\": \"Absent Human Backstop\",\n      \"definition\": \"No human authority can halt, reverse, or reinterpret automated execution, so cryptographic or procedural correctness substitutes for trust and fails to produce it.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"No named party can halt execution\",\n        \"No escalation path exists from automated outcome to human judgment\",\n        \"Human interpretation is not stated to prevail where the two diverge\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:3808873-042\",\n          \"url\": \"https://wulfkaal.github.io/claims/3808873-042\"\n        },\n        {\n          \"id\": \"kaal:claim:5886342-009\",\n          \"url\": \"https://wulfkaal.github.io/claims/5886342-009\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:3373393-038\",\n        \"url\": \"https://wulfkaal.github.io/claims/3373393-038\",\n        \"year\": \"2019\",\n        \"mechanism\": \"without a decentralized human backstop to code, cryptographic security does not create trust between principals and agents\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"legal-personality-and-liability-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/legal-personality-and-liability-gap.json\"\n        },\n        {\n          \"slug\": \"smart-contract-rigidity\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/smart-contract-rigidity.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F016\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F017\",\n      \"class\": \"E\",\n      \"class_name\": \"Evaluation and Feedback\",\n      \"name\": \"Feedback Degradation Above Evaluator Capability\",\n      \"definition\": \"Human or agent evaluation degrades precisely where the evaluated system is hardest to evaluate, including where it exceeds the evaluator.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Evaluators score outputs they cannot independently verify\",\n        \"The evaluated system is at or above evaluator capability in the domain\",\n        \"Evaluator agreement is used as the quality signal\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:4855607-018\",\n          \"url\": \"https://wulfkaal.github.io/claims/4855607-018\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"ai-oversight-and-alignment-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/ai-oversight-and-alignment-gap.json\"\n        },\n        {\n          \"slug\": \"measurement-and-metric-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/measurement-and-metric-failure.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F017\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F018\",\n      \"class\": \"E\",\n      \"class_name\": \"Evaluation and Feedback\",\n      \"name\": \"Unstaked Adjudication\",\n      \"definition\": \"Whoever judges a contribution risks nothing on the judgment, so judgment is cheap and drifts.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Validators or reviewers stake nothing on their verdict\",\n        \"Verdicts are not contestable within a stated window\",\n        \"No standing consequence follows from a verdict later shown wrong\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5245185-036\",\n          \"url\": \"https://wulfkaal.github.io/claims/5245185-036\"\n        }\n      ],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2486570-031\",\n        \"url\": \"https://wulfkaal.github.io/claims/2486570-031\",\n        \"year\": \"2014\",\n        \"mechanism\": \"consequence attaching to the adjudicating party as the source of care\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"reputation-system-gaming\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/reputation-system-gaming.json\"\n        },\n        {\n          \"slug\": \"board-and-oversight-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/board-and-oversight-failure.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F018\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F019\",\n      \"class\": \"E\",\n      \"class_name\": \"Evaluation and Feedback\",\n      \"name\": \"Training and Annotation Bias Propagation\",\n      \"definition\": \"Bias in annotators or automated labeling propagates into the model and then into every decision the agent makes.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Labels are produced by a narrow annotator pool or by another model\",\n        \"No demographic or scenario stratification is checked\",\n        \"Label provenance is not recorded\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5095633-019\",\n          \"url\": \"https://wulfkaal.github.io/claims/5095633-019\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"ai-model-and-training-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/ai-model-and-training-failure.json\"\n        },\n        {\n          \"slug\": \"data-quality-and-comparability\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/data-quality-and-comparability.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F019\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F020\",\n      \"class\": \"E\",\n      \"class_name\": \"Evaluation and Feedback\",\n      \"name\": \"Human Judgment Displacement\",\n      \"definition\": \"Automation replaces judgment in a setting that required judgment, and the loss is not detected because the output still looks well formed.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Output is fluent and confident regardless of correctness\",\n        \"No sampled human review of accepted outputs occurs\",\n        \"The prior human process left no record to compare against\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2267560-025\",\n        \"url\": \"https://wulfkaal.github.io/claims/2267560-025\",\n        \"year\": \"2013\",\n        \"mechanism\": \"decision makers relying on presumptively optimal rules for want of decentralized information\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"human-judgment-displacement\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/human-judgment-displacement.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F020\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F021\",\n      \"class\": \"F\",\n      \"class_name\": \"Coordination and Collusion\",\n      \"name\": \"Mutual Audit Capture\",\n      \"definition\": \"Agents assigned to oversee one another converge on mutual approval, so peer monitoring devolves into self serving behavior.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Agents both audit and are audited by the same population\",\n        \"No anti collusion constraint or randomized assignment applies\",\n        \"Approval is cheaper for the auditor than refusal\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:5245185-010\",\n          \"url\": \"https://wulfkaal.github.io/claims/5245185-010\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"reputation-system-gaming\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/reputation-system-gaming.json\"\n        },\n        {\n          \"slug\": \"board-and-oversight-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/board-and-oversight-failure.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F021\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F022\",\n      \"class\": \"F\",\n      \"class_name\": \"Coordination and Collusion\",\n      \"name\": \"Collusion Rings and Reciprocal Validation\",\n      \"definition\": \"A subset of agents validates one another to manufacture standing, and formal mechanism design alone does not detect it.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Validation is reciprocal or citation-like\",\n        \"One party can field several competing agents per task\",\n        \"No ring detection or downranking of reciprocal patterns is applied\"\n      ],\n      \"grounding_claims\": [\n        {\n          \"id\": \"kaal:claim:6192998-031\",\n          \"url\": \"https://wulfkaal.github.io/claims/6192998-031\"\n        }\n      ],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"reputation-system-gaming\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/reputation-system-gaming.json\"\n        },\n        {\n          \"slug\": \"consensus-and-protocol-attack\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/consensus-and-protocol-attack.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F022\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F023\",\n      \"class\": \"F\",\n      \"class_name\": \"Coordination and Collusion\",\n      \"name\": \"Collective Action and Coordination Failure\",\n      \"definition\": \"Individually rational agent behavior produces a collectively worse outcome and no mechanism reconciles the two.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Payoff to defection exceeds payoff to cooperation in a single interaction\",\n        \"Interactions are not expected to repeat, or identity does not persist across them\",\n        \"No mechanism prices the externality\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2267560-027\",\n        \"url\": \"https://wulfkaal.github.io/claims/2267560-027\",\n        \"year\": \"2013\",\n        \"mechanism\": \"private parties acting on decentralized information without a reconciling mechanism\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"collective-action-and-coordination-failure\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/collective-action-and-coordination-failure.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F023\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F024\",\n      \"class\": \"F\",\n      \"class_name\": \"Coordination and Collusion\",\n      \"name\": \"Delegation Opportunism\",\n      \"definition\": \"An agent acting for a principal, or for another agent, captures private benefit at the principal's expense, and monitoring costs more than it recovers.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"The delegation chain is more than one link deep\",\n        \"The principal cannot observe intermediate actions\",\n        \"The agent's objective is not identical to the principal's\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:3373393-003\",\n        \"url\": \"https://wulfkaal.github.io/claims/3373393-003\",\n        \"year\": \"2019\",\n        \"mechanism\": \"agency conflicts from separation of ownership and control cannot be fully addressed because monitoring is costly\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"agency-cost-and-managerial-opportunism\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/agency-cost-and-managerial-opportunism.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F024\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F025\",\n      \"class\": \"G\",\n      \"class_name\": \"Execution and Inputs\",\n      \"name\": \"Oracle and Input Corruption\",\n      \"definition\": \"The mechanism executes correctly on an input that is wrong, stale, manipulated, or injected.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Any input crosses a trust boundary without attestation\",\n        \"A single source can determine an input value\",\n        \"No staleness bound or sanity range is enforced\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"oracle-and-input-corruption\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/oracle-and-input-corruption.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F025\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F026\",\n      \"class\": \"G\",\n      \"class_name\": \"Execution and Inputs\",\n      \"name\": \"Automated Execution Rigidity\",\n      \"definition\": \"Execution cannot accommodate circumstances the code did not anticipate, and cannot be amended in time to matter.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Execution is irreversible once triggered\",\n        \"Amendment requires a process slower than the harm\",\n        \"No circuit breaker or pause authority exists\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2267560-012\",\n        \"url\": \"https://wulfkaal.github.io/claims/2267560-012\",\n        \"year\": \"2013\",\n        \"mechanism\": \"rules are adaptable only where the process producing them integrates dynamic elements\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"smart-contract-rigidity\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/smart-contract-rigidity.json\"\n        },\n        {\n          \"slug\": \"rule-obsolescence-and-ossification\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/rule-obsolescence-and-ossification.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F026\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F027\",\n      \"class\": \"G\",\n      \"class_name\": \"Execution and Inputs\",\n      \"name\": \"Code Defect Exploitation\",\n      \"definition\": \"A defect in deployed code is exercised by an adversary before it is found by its authors.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Code holds value or authority and is publicly reachable\",\n        \"No independent audit or adversarial review preceded deployment\",\n        \"Upgrade path is absent or itself unguarded\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"smart-contract-bug-and-exploit\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/smart-contract-bug-and-exploit.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F027\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F028\",\n      \"class\": \"G\",\n      \"class_name\": \"Execution and Inputs\",\n      \"name\": \"Custody and Key Compromise\",\n      \"definition\": \"Control of an agent's identity, assets, or authority is lost or captured through key or custody failure.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"An agent holds signing authority without threshold or rotation\",\n        \"Key material is reachable by the same process that uses it\",\n        \"No recovery path distinguishes loss from theft\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": null,\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"custody-and-key-loss\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/custody-and-key-loss.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F028\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F029\",\n      \"class\": \"H\",\n      \"class_name\": \"Structure and Drift\",\n      \"name\": \"Recentralization Drift\",\n      \"definition\": \"A system designed to distribute authority concentrates it again through tooling, delegation, capital, or expertise asymmetry.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"A small number of operators run most infrastructure or most agents\",\n        \"Delegation is permitted and defaults are sticky\",\n        \"Participation cost rises with system maturity\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2273857-062\",\n        \"url\": \"https://wulfkaal.github.io/claims/2273857-062\",\n        \"year\": \"2013\",\n        \"mechanism\": \"concentration of institution specific information in few hands\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"recentralization-drift\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/recentralization-drift.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F029\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F030\",\n      \"class\": \"H\",\n      \"class_name\": \"Structure and Drift\",\n      \"name\": \"Rule Obsolescence and Ossification\",\n      \"definition\": \"A rule persists after the conditions that justified it have changed, and resists revision.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Amendment requires a supermajority of a population that has stopped participating\",\n        \"No scheduled review of parameters against outcomes exists\",\n        \"Parameters were set once at launch\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2267560-012\",\n        \"url\": \"https://wulfkaal.github.io/claims/2267560-012\",\n        \"year\": \"2013\",\n        \"mechanism\": \"adaptability requires dynamic elements in the rulemaking process itself\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"rule-obsolescence-and-ossification\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/rule-obsolescence-and-ossification.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F030\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F031\",\n      \"class\": \"H\",\n      \"class_name\": \"Structure and Drift\",\n      \"name\": \"Participation Collapse\",\n      \"definition\": \"Eligible participants stop participating, leaving decisions to a small, self selected, or unrepresentative remainder.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"Participation is unrewarded or costs more than it returns\",\n        \"Quorum is defined against eligible rather than active population\",\n        \"Decision volume exceeds attention available\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:2715083-020\",\n        \"url\": \"https://wulfkaal.github.io/claims/2715083-020\",\n        \"year\": \"2016\",\n        \"mechanism\": \"board independence contingent on who actually exercises the function\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"governance-participation-collapse\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/governance-participation-collapse.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F031\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    },\n    {\n      \"id\": \"AFMR-F032\",\n      \"class\": \"H\",\n      \"class_name\": \"Structure and Drift\",\n      \"name\": \"Enforcement and Liability Gap\",\n      \"definition\": \"A rule exists and cannot be enforced, or no recognized person bears the obligation, so liability has nowhere to attach.\",\n      \"status\": \"stable\",\n      \"trigger_conditions\": [\n        \"No legal person is identifiable behind the agent\",\n        \"The obligated party is outside the reach of any enforcing authority\",\n        \"Sanction depends on a party that can exit at will\"\n      ],\n      \"grounding_claims\": [],\n      \"institutional_antecedent\": {\n        \"id\": \"kaal:claim:3373393-038\",\n        \"url\": \"https://wulfkaal.github.io/claims/3373393-038\",\n        \"year\": \"2019\",\n        \"mechanism\": \"procedural correctness failing to substitute for an accountable party\"\n      },\n      \"corpus_failure_families\": [\n        {\n          \"slug\": \"enforcement-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/enforcement-gap.json\"\n        },\n        {\n          \"slug\": \"legal-personality-and-liability-gap\",\n          \"url\": \"https://wulfkaal.github.io/failures/by-name/legal-personality-and-liability-gap.json\"\n        }\n      ],\n      \"canonical_url\": \"https://wulfkaal.github.io/afmr/AFMR-F032\",\n      \"crosswalk\": {\n        \"nist_ai_rmf\": [],\n        \"iso_42001\": [],\n        \"eu_ai_act\": [],\n        \"mit_ai_risk_repository\": [],\n        \"owasp_llm\": [],\n        \"mitre_atlas\": []\n      }\n    }\n  ]\n}\n",
                "uri": "https://wulfkaal.github.io/afmr/index.json"
              }
            ]
          }
        },
        "resource_uri": "https://wulfkaal.github.io/afmr/index.json",
        "url": "https://afmr.ai/api/rpc"
      },
      "latency_ms": 116.77,
      "status": "ok"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-11-25"
        },
        "http_status": 200,
        "payload": {
          "id": 5,
          "jsonrpc": "2.0",
          "result": {
            "resources": [
              {
                "description": "AFMR 1.0 machine index: 32 permanent failure-mode families in eight classes.",
                "mimeType": "application/json",
                "name": "Canonical AFMR failure-mode registry",
                "uri": "https://wulfkaal.github.io/afmr/index.json"
              },
              {
                "description": "Normative AFMR 1.0 specification.",
                "mimeType": "text/html",
                "name": "AFMR 1.0 specification",
                "uri": "https://wulfkaal.github.io/afmr/spec-1.0.html"
              },
              {
                "description": "Authoritative discovery links for AFMR.ai.",
                "mimeType": "application/json",
                "name": "AFMR discovery document",
                "uri": "https://afmr.ai/.well-known/afmr.json"
              },
              {
                "description": "Working Draft 0.1 schema for a signed, scoped, lifecycle-aware AFMR reputation attestation.",
                "mimeType": "application/schema+json",
                "name": "Reputation attestation schema",
                "uri": "https://afmr.ai/standards/reputation-attestation/0.1/schema.json"
              },
              {
                "description": "Deterministic validation, proof, scope, evidence, and lifecycle requirements.",
                "mimeType": "application/json",
                "name": "Reputation attestation verifier requirements",
                "uri": "https://afmr.ai/standards/reputation-attestation/0.1/verifier.json"
              },
              {
                "description": "Intentionally empty pre-publication registry; no endpoint conformance is currently claimed.",
                "mimeType": "application/json",
                "name": "Conforming governance-endpoint registry",
                "uri": "https://afmr.ai/registries/endpoints/v0.1/index.json"
              },
              {
                "description": "Configuration-only empty index. No measured lift results or safety claims are published.",
                "mimeType": "application/json",
                "name": "Lift evidence public-card index",
                "uri": "https://afmr.ai/lift-evidence/index.json"
              },
              {
                "description": "Canonical stable redacted public-card contract for configuration-scoped cohort comparisons.",
                "mimeType": "application/schema+json",
                "name": "Lift comparison public-card schema",
                "uri": "https://wulfkaal.github.io/afmr/schemas/lift-comparison-public-card-v1.schema.json"
              }
            ]
          }
        },
        "url": "https://afmr.ai/api/rpc"
      },
      "latency_ms": 565.43,
      "status": "ok"
    },
    "server_card": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://afmr.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://afmr.ai/.well-known/mcp/server-card.json"
      },
      "latency_ms": 302.05,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "protocol_version": "2025-03-26",
        "reason": "no_session_id",
        "resume_expected": true,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "step_up_auth_probe": {
      "details": {
        "auth_required_checks": [],
        "broad_scopes": [],
        "challenge_headers": [],
        "minimal_scope_documented": false,
        "oauth_present": false,
        "scope_specificity_ratio": 0.0,
        "step_up_signals": [],
        "supported_scopes": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tool_snapshot_probe": {
      "details": {
        "current_tool_count": 4,
        "reason": "no_historical_snapshot"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-11-25"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true
                },
                "description": "Return canonical AFMR specifications, registries, schemas, endpoints, and scope boundaries.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "discover_afmr",
                "title": "Discover AFMR resources"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true
                },
                "description": "Find exact AFMR 1.0 failure-mode records by permanent ID or bounded text query.",
                "inputSchema": {
                  "additionalProperties": false,
                  "anyOf": [
                    {
                      "required": [
                        "id"
                      ]
                    },
                    {
                      "required": [
                        "query"
                      ]
                    }
                  ],
                  "properties": {
                    "id": {
                      "description": "Exact permanent family identifier, for example AFMR-F010.",
                      "pattern": "^AFMR-F[0-9]{3}$",
                      "type": "string"
                    },
                    "limit": {
                      "default": 5,
                      "maximum": 10,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Text matched against ID, name, definition, and class.",
                      "maxLength": 100,
                      "minLength": 2,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "lookup_failure_mode",
                "title": "Look up AFMR failure modes"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true
                },
                "description": "Return the portable attestation, trust-profile, verifier-result, endpoint-registry, and lifecycle contracts.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "get_reputation_attestation_contract",
                "title": "Get the reputation-attestation contract"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true
                },
                "description": "Return the stable configuration-scoped public-card schema and empty public index; no results are asserted.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "get_lift_evidence_contract",
                "title": "Get the Lift Evidence public-card contract"
              }
            ]
          }
        },
        "url": "https://afmr.ai/api/rpc"
      },
      "latency_ms": 47.67,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-11-25"
        },
        "bad_protocol_payload": {
          "id": 410,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true
                },
                "description": "Return canonical AFMR specifications, registries, schemas, endpoints, and scope boundaries.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "discover_afmr",
                "title": "Discover AFMR resources"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true
                },
                "description": "Find exact AFMR 1.0 failure-mode records by permanent ID or bounded text query.",
                "inputSchema": {
                  "additionalProperties": false,
                  "anyOf": [
                    {
                      "required": [
                        "id"
                      ]
                    },
                    {
                      "required": [
                        "query"
                      ]
                    }
                  ],
                  "properties": {
                    "id": {
                      "description": "Exact permanent family identifier, for example AFMR-F010.",
                      "pattern": "^AFMR-F[0-9]{3}$",
                      "type": "string"
                    },
                    "limit": {
                      "default": 5,
                      "maximum": 10,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Text matched against ID, name, definition, and class.",
                      "maxLength": 100,
                      "minLength": 2,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "lookup_failure_mode",
                "title": "Look up AFMR failure modes"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true
                },
                "description": "Return the portable attestation, trust-profile, verifier-result, endpoint-registry, and lifecycle contracts.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "get_reputation_attestation_contract",
                "title": "Get the reputation-attestation contract"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true
                },
                "description": "Return the stable configuration-scoped public-card schema and empty public index; no results are asserted.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "get_lift_evidence_contract",
                "title": "Get the Lift Evidence public-card contract"
              }
            ]
          }
        },
        "bad_protocol_status_code": 200,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id",
          "bad_protocol_not_rejected"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": true,
        "requested_protocol_version": "2025-03-26",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 53.12,
      "status": "error"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": {
            "type": "resource",
            "uri": "https://wulfkaal.github.io/afmr/index.json"
          }
        },
        "initialize_capability_keys": [
          "resources",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 200,
          "probe_status": "missing"
        }
      },
      "latency_ms": 56.05,
      "status": "missing"
    }
  },
  "failures": {
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Client error '404 Not Found' for url 'https://afmr.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://afmr.ai/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Client error '404 Not Found' for url 'https://afmr.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://afmr.ai/.well-known/mcp/server-card.json"
    },
    "transport_compliance_probe": {
      "bad_protocol_error": null,
      "bad_protocol_headers": {
        "content-type": "application/json",
        "mcp-protocol-version": "2025-11-25"
      },
      "bad_protocol_payload": {
        "id": 410,
        "jsonrpc": "2.0",
        "result": {
          "tools": [
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true
              },
              "description": "Return canonical AFMR specifications, registries, schemas, endpoints, and scope boundaries.",
              "inputSchema": {
                "additionalProperties": false,
                "properties": {},
                "type": "object"
              },
              "name": "discover_afmr",
              "title": "Discover AFMR resources"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": true,
                "readOnlyHint": true
              },
              "description": "Find exact AFMR 1.0 failure-mode records by permanent ID or bounded text query.",
              "inputSchema": {
                "additionalProperties": false,
                "anyOf": [
                  {
                    "required": [
                      "id"
                    ]
                  },
                  {
                    "required": [
                      "query"
                    ]
                  }
                ],
                "properties": {
                  "id": {
                    "description": "Exact permanent family identifier, for example AFMR-F010.",
                    "pattern": "^AFMR-F[0-9]{3}$",
                    "type": "string"
                  },
                  "limit": {
                    "default": 5,
                    "maximum": 10,
                    "minimum": 1,
                    "type": "integer"
                  },
                  "query": {
                    "description": "Text matched against ID, name, definition, and class.",
                    "maxLength": 100,
                    "minLength": 2,
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "name": "lookup_failure_mode",
              "title": "Look up AFMR failure modes"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true
              },
              "description": "Return the portable attestation, trust-profile, verifier-result, endpoint-registry, and lifecycle contracts.",
              "inputSchema": {
                "additionalProperties": false,
                "properties": {},
                "type": "object"
              },
              "name": "get_reputation_attestation_contract",
              "title": "Get the reputation-attestation contract"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true
              },
              "description": "Return the stable configuration-scoped public-card schema and empty public index; no results are asserted.",
              "inputSchema": {
                "additionalProperties": false,
                "properties": {},
                "type": "object"
              },
              "name": "get_lift_evidence_contract",
              "title": "Get the Lift Evidence public-card contract"
            }
          ]
        }
      },
      "bad_protocol_status_code": 200,
      "delete_error": null,
      "delete_status_code": null,
      "expired_session_error": null,
      "expired_session_status_code": null,
      "issues": [
        "missing_session_id",
        "bad_protocol_not_rejected"
      ],
      "last_event_id_visible": false,
      "protocol_header_present": true,
      "requested_protocol_version": "2025-03-26",
      "session_id_present": false,
      "transport": "streamable-http"
    }
  },
  "remote_url": "https://afmr.ai/api/rpc",
  "server_card_payload": null,
  "server_identifier": "ai.afmr/discovery"
}

Known versions

Validation history

7 day score delta
n/a
30 day score delta
n/a
Recent healthy ratio
100%
Freshness
1.1h
TimestampStatusScoreLatencyTools
Jul 31, 2026 05:24:28 AM UTC Healthy 71.2 2113.1 ms 4

Validation timeline

ValidatedSummaryScoreProtocolAuth modeToolsHigh-risk toolsChanges
Jul 31, 2026 05:24:28 AM UTC Healthy 71.2 2025-03-26 public 4 1 none

Recent validation runs

StartedStatusSummaryLatencyChecks
Jul 31, 2026 05:24:26 AM UTC Completed Healthy 2113.1 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe