← Back to search

Search • Rankings • TrustOps • Docs • Pricing • Claim/Manage

ai.nothumansearch/search

Not Human Search

Search engine for AI agents. Find websites and APIs ranked by agentic readiness.

JSON report • Policy • Badge metadata • History API • • Global feed

DECISION SUMMARY

Block For Production

Score

3.8

Rank suppressed while production readiness shows a blocking verdict.

Confidence

Low

Based on evidence completeness, recency, and validation density.

Evidence age

9.7h old

Freshness: fresh. Snapshot trustsnap_c8e548ad009e66ab.

Top risk drivers

Utility Coverage
Tool Surface Design
Tool Snapshot Churn

Recommended actions

Make tools/list succeed unauthenticated when possible, or document the auth flow in the server card.
Allow initialize to succeed consistently, or return a deterministic auth-required response with clear metadata.
Compare initialize responses between the latest two runs and restore the previous stable behavior.

Next action

revalidate, add safeguards, export policy

score below evaluation threshold

Compare alternatives Export policy Open report JSON Dispute this assessment

Observed Attention

No observed attention

No observed attention in the current 30-day window.

No segmented attention signals observed in the current window.

Bucketed signal based on recent segmented Verify telemetry. Crawler and evaluator activity is not treated as confirmed human demand.

Risks Compatibility Evidence Fix it Governance History Technical details

Status

Unknown

Score

3.8

Transport

streamable-http

Tools

Ownership

Unclaimed

Claim, revalidate, or manage this server

DISPUTE THIS ASSESSMENT

Dispute this assessment

If any published claim about this server -- its score, a risk flag, a capability classification, or its taxonomy -- is factually wrong, tell us what evidence shows and we will review it. This does not require claiming or verifying ownership of the server first.

Verify responds to disputes within 5 business days and resolves them within 15.

Dispute history

No disputes filed for this server.

Risks

Security posture

Tools analyzed

High-risk tools

Destructive tools

Exec tools

Egress tools

Secret tools

Bulk-access tools

Risk distribution

none

Tool capability & risk inventory

No tool inventory available from the latest validation run.

Write-action governance

Governance status

Not_Assessed

Safe to publish

Auth boundary

public_or_unclear

Blast radius

Low

High-risk tools

Confirmation signals

none

Safeguard count

Status detail: No write-action governance evidence is available yet.

Tool	Risk	Flags	Safeguards
High-risk tool assessment unavailable -- no tools were analyzed.

Action-controls diff

Snapshot changed

yes

Disabled-by-default candidates

none

New actions

Action	Risk	Flags
No newly added actions.

Changed actions

Action	Change types	Risk
No materially changed actions.

Critical alerts

High/critical-severity alerts

Production verdicts degrade quickly when high or critical-severity alerts are active.

Compatibility

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

Not client-compatible

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Initialize must be reachable.; tools/list must succeed.; Transport compliance failed or did not complete successfully.; Step-up auth signals should be documented and connector-friendly.

Confidence: low (46.25)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • Not_Assessed
tools_list • Not_Assessed
transport_compliance_probe • Not_Assessed
step_up_auth_probe • Not_Assessed
connector_replay_probe • Not_Assessed — Frozen tool snapshots must survive refresh.
request_association_probe • Not_Assessed — Roots, sampling, and elicitation should stay request-scoped.

Client compatibility: Claude

Not client-compatible

Initialize must succeed or cleanly request auth.; tools/list must succeed.; Transport behavior should match Claude-compatible HTTP expectations.; The tool surface is not limited to search/fetch-style read tools.; OAuth is not configured, so this client cannot authenticate without additional setup.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.

Confidence: low (46.25)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • Not_Assessed
tools_list • Not_Assessed
transport_compliance_probe • Not_Assessed

Write-action publishing

Publishing blocked

action_safety_probe has not run yet -- no tool surface was observed, so write-action safety could not be assessed. Active alert(s) affecting production readiness: Score dropped materially, Initialize flow regressed, tools/list regressed.

Confidence: low (46.25)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history

Disagreements: none

action_safety_probe • Not_Assessed

Snapshot churn risk

Medium

The live tool surface changed between recent validations.

Confidence: low (46.25)

Evidence provenance

Winner: history

Supporting sources: history, live_validation

Disagreements: none

tool_snapshot_probe • Not_Assessed
connector_replay_probe • Not_Assessed

Client compatibility gate details

ChatGPT custom connector

Not client-compatible

Remediation checklist

Add OAuth-based authentication for remote connector auth.
Support dynamic client registration (DCR) to simplify connector setup.
Fix the server so its initialize handshake succeeds.
Fix the server so tools/list returns successfully.
Resolve the transport compliance failure -- see the transport compliance probe evidence for what specifically broke.
Document step-up auth requirements in a connector-friendly way.

Claude remote MCP

Not client-compatible

Remediation checklist

Fix the server so initialize succeeds or cleanly requests auth.
Fix the server so tools/list returns successfully.
Resolve the transport compliance failure -- see the transport compliance probe evidence for what specifically broke.
Limit the exposed surface to search/fetch-style read tools.
Configure OAuth for authenticated remote MCP access.
Remove export, bulk, mutating, and high-blast-radius exposure before certifying company-knowledge use.

Write-safe publishing

Blocked

Production readiness is blocked by an active alert: Score dropped materially.; Production readiness is blocked by an active alert: Initialize flow regressed.; Production readiness is blocked by an active alert: tools/list regressed.

Remediation checklist

Resolve the active alert: Score dropped materially.
Resolve the active alert: Initialize flow regressed.
Resolve the active alert: tools/list regressed.

Verdict traces

Production verdict

Needs remediation

Current validation evidence shows operational or discovery gaps that should be fixed first.

Confidence: low (46.25)

Winning source: metadata

Triggering alerts

score_drop • high • Score dropped materially
tool_count_drop • medium • Tool count decreased
initialize_regressed • critical • Initialize flow regressed
tools_list_regressed • critical • tools/list regressed
tool_snapshot_changed • high • Tool snapshot changed
auth_mode_changed • high • Auth mode changed

Client verdict trace table

Verdict	Status	Checks	Winning source	Conflicts
`openai_connectors`	Not client-compatible	initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe	live_validation	none
`claude_desktop`	Not 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`	Medium	tool_snapshot_probe, connector_replay_probe	history	none

Publishability policy profiles

ChatGPT custom connector compatibility

Not connector-compatible

Search Fetch Only: No
Write Actions Present: No
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Claude remote MCP compatibility

Not connector-compatible

Search Fetch Only: No
Write Actions Present: No
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

remote_http_endpoint: Passes
oauth_discovery: Degraded
frozen_tool_snapshot_refresh: Passes
request_association: Likely to fail

Anthropic remote MCP fixture

Degraded

Initialize must succeed or cleanly request auth.; tools/list must succeed.; Transport behavior should match Claude-compatible HTTP expectations.

remote_transport: Passes
tool_discovery: Likely to fail
auth_connect: Likely to fail
safe_write_review: Degraded

Recommended for

Metadata-first exploration only

Evidence confidence is still low, so verify the server manually before depending on it.

Evidence

Current trust snapshot

Snapshot ID

trustsnap_c8e548ad009e66ab

Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.

Snapshot generated

Aug 11, 2026 05:22:06 PM UTC

All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.

Last validated

Aug 11, 2026 07:38:00 AM UTC

Age: 9.74h • evidence age tier: Verified in last 24h • display score: 3.75

Canonical machine links

Compare index

/compare.json

Compare API

/v1/compare?server=ai.nothumansearch%2Fsearch

Trust summary

/v1/servers/ai.nothumansearch/search/trust-summary

Report JSON

/v1/servers/ai.nothumansearch/search/report

Policy export

/v1/servers/ai.nothumansearch/search/policy

Badge metadata

/v1/servers/ai.nothumansearch/search/badge

Ledger evidence

/v1/servers/ai.nothumansearch/search/ledger

Human compare URL

/compare?server=ai.nothumansearch%2Fsearch

Evidence confidence

Confidence score

46.2

Based on 1 recent validations, 0 captured checks, and validation age of 9.7 hours.

Live checks captured

More direct checks increase trust in the current verdict.

Validation age

9.7h

Lower age means fresher evidence.

Latest validation evidence

Latest summary

Unknown

Validation profile

remote_mcp

Started

Aug 11, 2026 07:37:50 AM UTC

Latency

10111.5 ms

Failures

probe_noise_resilience The read operation timed out

Checks

Check	Status	Latency	Evidence
`action_safety_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`advanced_capabilities_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`connector_publishability_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`connector_replay_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`determinism_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`initialize`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`interactive_flow_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`oauth_authorization_server`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`oauth_protected_resource`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`official_registry_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`openid_configuration`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`probe_noise_resilience`	Error	10086.2 ms	The read operation timed out
`prompt_get`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`prompts_list`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`protocol_version_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`provenance_divergence_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`request_association_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`resource_read`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`resources_list`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`schema_divergence_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`server_card`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`session_resume_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`step_up_auth_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`tool_snapshot_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`tools_list`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`transport_compliance_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.
`utility_coverage_probe`	Not_Assessed	n/a	Not assessed -- robots.txt consent could not be confirmed.

Known versions

1.0.0

Public server reputation

Validation success 7d

1.0

Validation success 30d

1.0

Mean time to recover

n/a

Breaking diffs 30d

Registry drift frequency 30d

Snapshot changes 30d

Benchmark tasks

Benchmark task	Status	Evidence
Discover tools	Likely to fail	`initialize` • Not_Assessed `tools_list` • Not_Assessed
Read-only fetch flow	Likely to fail	`resource_read` • Not_Assessed `read_only_tool_surface` • Missing
OAuth-required connect	Degraded	`oauth_protected_resource` • Not_Assessed `step_up_auth_probe` • Not_Assessed
Safe write flow with confirmation	Likely to fail	`action_safety_probe` • Not_Assessed

Utility coverage

Probe status

Not_Assessed

Completions

not detected

Completion probe target: none

Pagination

not detected

No nextCursor evidence.

Tasks

Missing

Advertised: no

Tool snapshot diff & changelog

Snapshot changed

yes

Added tools

none

Removed tools

check_url find_mcp_servers get_site_details get_stats get_top_sites handoff_provider_action list_categories prepare_provider_action recent_additions record_action_interest register_monitor search_agents submit_site verify_mcp

Required-argument changes

Tool	Added required args	Removed required args
No required-argument changes detected.

Output-schema drift

Tool	Previous properties	Latest properties
No output-schema drift detected.

Validation diff

Score delta

-59.73

Summary changed

yes

Tool delta

-14

Prompt delta

Auth mode changed

yes

Write surface expanded

Protocol regressed

Registry drift changed

Regressed checks: action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, utility_coverage_probe

Improved checks: oauth_protected_resource, server_card, transport_compliance_probe

Newly assessed dimensions: none

No longer assessed dimensions: abuse_noise_ratio_score, action_safety_score, destructive_operation_safety_score, egress_ssrf_resilience_score, execution_sandbox_safety_score, least_privilege_scope_score, secret_handling_hygiene_score, transport_compliance_score

Component	Previous	Latest	Delta
`interactive_flow_safety_score`	4.0	0.0	-4.0
`session_semantics_score`	4.0	0.0	-4.0
`task_success_score`	4.0	0.0	-4.0
`tool_capability_clarity_score`	4.0	0.0	-4.0
`tool_namespace_clarity_score`	4.0	0.0	-4.0
`tool_snapshot_churn_score`	4.0	0.0	-4.0
`backward_compatibility_score`	4.0	1.0	-3.0
`connector_publishability_score`	3.0	0.0	-3.0

Registry & provenance divergence

Probe status

Not_Assessed

Direct official match

Drift fields

none

Cross-registry alias disagreements

none

Field	Registry	Live server card
Title	n/a	n/a
Version	n/a	n/a
Homepage	n/a	n/a

Active alerts

Score dropped materially (high)
Score fell by 59.7 points versus the previous run.
Tool count decreased (medium)
Advertised tool count dropped by 14.
Initialize flow regressed (critical)
A client-visible initialize behavior changed for the worse.
tools/list regressed (critical)
Tool discovery became less reliable on the latest run.
Tool snapshot changed (high)
Tools were added, removed, or materially changed between the latest two validations.
Auth mode changed (high)
Auth mode changed from public to unknown.

Aliases & registry graph

Identifier	Source	Canonical	Identity evidence	Score
`ai.nothumansearch/search`	official_registry	yes	canonical	3.8

Alias consolidation

Strong alias identity requires matching remote URL, server-card URL, repository slug, or explicit registry cross-reference; shared provider namespace alone is not identity.

Canonical identifier

ai.nothumansearch/search

Duplicate aliases

Registry sources

official_registry

Remote URLs

https://nothumansearch.ai/mcp

Homepages

https://nothumansearch.ai

Source disagreements

Field	What differs	Observed values
No source disagreements detected.

Fix it

Why this score?

Access & Protocol

5/44

Connectivity, auth, and transport expectations for common clients.

Interface Quality

7/56

How well the tool/resource interface communicates and behaves under automation.

Security Posture

0/36

How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.

Reliability & Trust

10/24

Operational stability, consistency, and trustworthiness over time.

Discovery & Governance

14/28

How well the server is documented, listed, and governed in public registries.

Adoption & Market

2/8

Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability

0/4

Measures whether auth discovery and protected access behave predictably for clients.

Error Contract Quality

0/4

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

0/4

Completeness of tool descriptions, parameter docs, examples, and schema shape.

Backward Compatibility

1/4

Stability score across tool schema/name drift relative to prior validations.

SLO Health

3/4

Availability, latency, and burst-failure profile across recent validation history.

Security Hygiene

0/4

HTTPS posture, endpoint hygiene, and response-surface hardening checks.

Task Success

0/4

Can an agent reliably initialize, enumerate tools, and execute core MCP flows?

Trust Confidence

3/4

Confidence-adjusted reliability score that penalizes low evidence volume.

Prompt Contract

2/4

Quality of prompt metadata, argument shape, and prompt discoverability for clients.

Resource Contract

2/4

How completely resources and resource templates describe URIs, types, and usage shape.

Discovery Metadata

2/4

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

1/4

How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.

Session Semantics

0/4

Determinism and state behavior across repeated MCP calls, including sticky-session surprises.

Tool Surface Design

0/4

Naming clarity, schema ergonomics, and parameter complexity across the tool surface.

Result Shape Stability

0/4

Stability of declared output schemas across validations, with penalties for drift or missing shapes.

OAuth Interop

0/4

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

2/4

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

1/4

Whether declared transport metadata matches the observed endpoint behavior and response formats.

Spec Recency

0/4

How close the server’s claimed MCP protocol version is to the latest known public revision.

Session Resume

1/4

Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.

Step-Up Auth

1/4

Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.

Utility Coverage

0/4

Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.

Advanced Capability Coverage

0/4

Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.

Connector Publishability

0/4

How ready the server looks for client catalogs and managed connector programs.

Tool Snapshot Churn

0/4

Stability of the tool surface across recent validations, including add/remove and output-shape drift.

Connector Replay

1/4

Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.

Request Association

1/4

Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.

Interactive Flow Safety

0/4

Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.

Official Registry Presence

4/4

Whether the server appears directly or indirectly in the official MCP registry.

Safety Transparency

2/4

Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.

Tool Capability Clarity

0/4

How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.

Data Exfiltration Resilience

0/4

Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.

Supply Chain Signal

1/4

Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.

Input Sanitization Safety

0/4

Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.

Tool Namespace Clarity

0/4

Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

9 component(s) not assessed for this run: Abuse/Noise Resilience, Transport Compliance, Action Safety, Provenance Divergence, Destructive Operation Safety, Egress / SSRF Resilience, Execution / Sandbox Safety, Least Privilege Scope, Secret Handling Hygiene

Experimental candidate components

Personal Data Exposure

1.5

Experimental candidate, weight 0. Export and bulk-access evidence only; no impact on totals, verdicts, rankings, or gates.

Actionable remediation

Severity	Remediation	Why it matters	Recommended action
Critical	Ensure tools/list succeeds consistently	Tools discovery is the minimum viable contract for most MCP clients and directories.	Make tools/list succeed unauthenticated when possible, or document the auth flow in the server card. Playbook Make `tools/list` deterministic across repeated calls. Document or relax auth requirements for discovery routes. Check that tool names, descriptions, and schemas remain stable across deploys.
Critical	Make initialize deterministic and client-friendly	If initialize fails or requires undocumented auth, many MCP clients cannot connect.	Allow initialize to succeed consistently, or return a deterministic auth-required response with clear metadata. Playbook Allow `initialize` to succeed unauthenticated when possible. If auth is required, return a deterministic auth-required response and matching metadata. Retest against `https://nothumansearch.ai/mcp` from a clean client session.
Critical	Respond to initialize flow regressed	A client-visible initialize behavior changed for the worse.	Compare initialize responses between the latest two runs and restore the previous stable behavior.
Critical	Respond to tools/list regressed	Tool discovery became less reliable on the latest run.	Compare tool enumeration outputs between runs and remove non-deterministic behavior.
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	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	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	Respond to auth mode changed	Auth mode changed from public to unknown.	Document the new auth posture and confirm protected-resource and challenge metadata still match reality.
High	Respond to score dropped materially	Score fell by 59.7 points versus the previous run.	Inspect the latest diff to find which checks and component scores regressed.
High	Respond to tool snapshot changed	Tools were added, removed, or materially changed between the latest two validations.	Publish a first-class changelog for tool additions, removals, and breaking schema changes. Playbook Review the tool snapshot diff for adds, removals, required-arg changes, and output-schema drift. Publish a changelog before managed connector clients refresh their frozen tool snapshots. Revalidate after the changelog and connector metadata are in sync.
Medium	Adopt a current MCP protocol revision	Older protocol revisions reduce compatibility with newer clients and registry programs.	Advertise a current MCP protocol revision (2025-06-18 or later) in both the initialize response and the MCP-Protocol-Version header. Playbook Update the server's advertised protocol version to a current MCP revision (2025-06-18 or later). Return the negotiated version consistently in both the `initialize` response and the `MCP-Protocol-Version` header. Revalidate and confirm `protocol_version_probe` reports `ok`.
Medium	Close connector-publishing gaps	Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability.
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 Serve `/.well-known/openid-configuration` with `issuer`, `jwks_uri`, `authorization_endpoint`, and `token_endpoint`. List supported grant types in `grant_types_supported` and scopes in `scopes_supported`. Revalidate and confirm the `openid_configuration` check returns `ok`.
Medium	Raise Access & Protocol score	Connectivity, auth, and transport expectations for common clients.	Tighten auth discovery, session behavior, and transport metadata until remote clients can connect without guesswork.
Medium	Raise Adoption & Market score	Adoption clues and public evidence that the server is intended for external use.	Increase external documentation and directory coverage so users can discover and evaluate the server.
Medium	Raise Interface Quality score	How well the tool/resource interface communicates and behaves under automation.	Improve schemas, error contracts, and recovery messages so agents can reason about the surface automatically.
Medium	Raise Security Posture score	How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.	Reduce destructive, egress, exec, secret, and freeform-input risk across the exposed tool surface. Playbook Classify each tool by read/write/delete/exec/network capability and confirm the classification is intentional. Gate high-risk tools behind scoped auth, narrow their schemas, and document safeguards such as allowlists or dry-run paths. Revalidate after the risky tools are tightened so the security posture score reflects the current surface.
Medium	Respond to tool count decreased	Advertised tool count dropped by 14.	Confirm whether the tool removal was intentional and, if so, publish an updated changelog.
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	Harden generic GET handling	Simple probe requests should not surface server instability or noisy failures.	Harden generic GET handlers around the origin of https://nothumansearch.ai/mcp so incidental traffic does not produce noisy failures.
Low	Publish newer MCP capability signals	Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking.	Advertise only the advanced capabilities (roots, sampling, elicitation) you have actually implemented end to end in the initialize capabilities object. Playbook Add the capabilities you actually support (`roots`, `sampling`, `elicitation`) to the `capabilities` object returned from `initialize`. Only advertise a capability once the corresponding request/response flow is implemented end to end. Revalidate and confirm `advanced_capabilities_probe` reflects the updated capability set.
Low	Publish or reconcile the server in the official MCP registry	Official registry presence improves discovery confidence and cross-source consistency.

Point loss breakdown

Component	Current	Points missing
Utility Coverage	0/4	-4.0
Tool Surface Design	0/4	-4.0
Tool Snapshot Churn	0/4	-4.0
Tool Namespace Clarity	0/4	-4.0
Tool Capability Clarity	0/4	-4.0
Task Success	0/4	-4.0
Spec Recency	0/4	-4.0
Session Semantics	0/4	-4.0
Security Hygiene	0/4	-4.0
Schema Completeness	0/4	-4.0
Result Shape Stability	0/4	-4.0
Recovery Semantics	0/4	-4.0

Compatibility profiles

OpenAI Connectors

22.2

blocked (2 of 9 requirements met)

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Claude Desktop

50.0

blocked (3 of 6 requirements met)

Initialize must succeed or cleanly request auth.; tools/list must succeed.; Transport behavior should match Claude-compatible HTTP expectations.

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Smithery

40.0

blocked (2 of 5 requirements met)

Tool discovery must succeed.; Initialize should work before execution.; Machine-readable failure semantics should be present.

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Generic Streamable HTTP

33.3

blocked (2 of 6 requirements met)

Initialize must succeed.; tools/list must succeed.; Transport behavior should match metadata.; Session behavior should be predictable.

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Governance

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.

Evidence age tier

Verified in last 24h

Policy SLA (contractual, distinct from the public 24h freshness window): 168.0h • confidence-weighted score (display score discounted for evidence age and confidence -- an internal TrustOps input, not the public score): 1.7 • evidence too old to display: ✕

Policy exports

Export policy

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

Verify Hosted MCP

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

none

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

score_below_hosting_threshold server_not_healthy_or_degraded latest_validation_not_passing blocked_by_active_alerts blocked_by_production_readiness

Deployment	Status	Endpoint	Release
No hosted runtime deployments yet.

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

Install snippets

Openai Connectors

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Claude Desktop

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Smithery

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Generic Http

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Unavailable Reason

No successful connection to this endpoint has been observed yet -- install instructions are withheld until initialize succeeds at least once.

Agent access & tool surface

Live server tools

No live tool surface captured yet.

Observed from the latest live validation against https://nothumansearch.ai/mcp. This is the target server surface, not Verify's own inspection tools.

Live capability counts

14 tools • 0 prompts • 0 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.nothumansearch/search.

Direct machine links

JSON report • Compare this server • Verify MCP API

History

Validation history

7 day score delta

n/a

30 day score delta

n/a

Recent healthy ratio

100%

Freshness

9.7h

Timestamp	Status	Score	Latency	Tools
Aug 11, 2026 07:38:00 AM UTC	Unknown	2.2	10111.5 ms	0
Aug 10, 2026 07:37:30 PM UTC	Healthy	62.0	1123.9 ms	14
Aug 10, 2026 07:37:11 AM UTC	Healthy	62.0	1355.9 ms	not fetched
Aug 09, 2026 07:37:05 PM UTC	Healthy	62.0	1100.7 ms	not fetched
Aug 09, 2026 07:36:48 AM UTC	Healthy	62.0	1230.5 ms	not fetched
Aug 08, 2026 07:36:26 PM UTC	Healthy	62.0	1087.2 ms	not fetched
Aug 08, 2026 07:36:18 AM UTC	Healthy	62.0	1013.7 ms	not fetched
Aug 07, 2026 07:36:01 PM UTC	Healthy	62.0	1422.0 ms	not fetched

Validation timeline

Validated	Summary	Score	Protocol	Auth mode	Tools	Changes
Aug 11, 2026 07:38:00 AM UTC	Unknown	n/a	unknown	unknown	0	summary_changed auth_mode_changed tool_snapshot_changed
Aug 10, 2026 07:37:30 PM UTC	Healthy	62.0	2025-06-18	public	14	none
Aug 10, 2026 07:37:11 AM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 09, 2026 07:37:05 PM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 09, 2026 07:36:48 AM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 08, 2026 07:36:26 PM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 08, 2026 07:36:18 AM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 07, 2026 07:36:01 PM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 07, 2026 07:35:50 AM UTC	Healthy	n/a	unknown	unknown	not fetched	none
Aug 06, 2026 07:35:35 PM UTC	Healthy	n/a	unknown	unknown	not fetched	none

Recent validation runs

Recent validation runs for this MCP server
Started	Status	Summary	Latency	Checks
Aug 11, 2026 07:37:50 AM UTC	Completed	Unknown	10111.5 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe (not counted in confidence)
Aug 10, 2026 07:37:29 PM UTC	Completed	Healthy	1123.9 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, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 10, 2026 07:37:10 AM UTC	Completed	Healthy	1355.9 ms	`not fetched (not counted in confidence)`
Aug 09, 2026 07:37:04 PM UTC	Completed	Healthy	1100.7 ms	`not fetched (not counted in confidence)`
Aug 09, 2026 07:36:47 AM UTC	Completed	Healthy	1230.5 ms	`not fetched (not counted in confidence)`
Aug 08, 2026 07:36:25 PM UTC	Completed	Healthy	1087.2 ms	`not fetched (not counted in confidence)`
Aug 08, 2026 07:36:17 AM UTC	Completed	Healthy	1013.7 ms	`not fetched (not counted in confidence)`
Aug 07, 2026 07:35:59 PM UTC	Completed	Healthy	1422.0 ms	`not fetched (not counted in confidence)`
Aug 07, 2026 07:35:48 AM UTC	Completed	Healthy	1155.3 ms	`not fetched (not counted in confidence)`
Aug 06, 2026 07:35:34 PM UTC	Completed	Healthy	1207.8 ms	`not fetched (not counted in confidence)`

Incident & change feed

Timestamp	Event	Details
Aug 11, 2026 07:38:00 AM UTC	Latest validation: unknown	Score 3.8 with status unknown.
Aug 11, 2026 07:38:00 AM UTC	Validation summary changed	Summary moved from healthy to unknown.
Aug 11, 2026 07:38:00 AM UTC	Score changed	Score delta -59.7 versus the previous run.
Aug 11, 2026 07:38:00 AM UTC	Tool snapshot changed	Added 0, removed 14, and changed 0 tool contracts.
Aug 11, 2026 07:38:00 AM UTC	Auth mode changed	Auth mode moved from public to unknown.
Aug 05, 2026 11:00:24 AM UTC	Score corrected (post-1.0.503 remediation, R1 zero-anchoring)	Prior: 67.82. Corrected: 64.92.

Technical details

Raw evidence view

Show raw JSON evidence

{
  "checks": {
    "action_safety_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "advanced_capabilities_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "connector_publishability_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "connector_replay_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "determinism_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "initialize": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "interactive_flow_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "oauth_authorization_server": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "oauth_protected_resource": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "official_registry_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "openid_configuration": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "probe_noise_resilience": {
      "details": {
        "consent_error": "robots.txt fetch failed; consent is unknown",
        "error": "The read operation timed out",
        "url": "https://nothumansearch.ai/robots.txt",
        "validation_disallowed": "unknown"
      },
      "latency_ms": 10086.22,
      "status": "error"
    },
    "prompt_get": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "prompts_list": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "protocol_version_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "provenance_divergence_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "request_association_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "resource_read": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "resources_list": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "schema_divergence_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "server_card": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "session_resume_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "step_up_auth_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "tool_snapshot_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "tools_list": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "transport_compliance_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    },
    "utility_coverage_probe": {
      "details": {
        "reason": "consent_unknown"
      },
      "latency_ms": null,
      "status": "not_assessed"
    }
  },
  "failures": {
    "probe_noise_resilience": {
      "consent_error": "robots.txt fetch failed; consent is unknown",
      "error": "The read operation timed out",
      "url": "https://nothumansearch.ai/robots.txt",
      "validation_disallowed": "unknown"
    }
  },
  "remote_url": "https://nothumansearch.ai/mcp",
  "server_card_payload": null,
  "server_identifier": "ai.nothumansearch/search"
}

Capabilities

OAuth: ✕
DCR/CIMD: ✕
Prompts: ✕
Homepage: https://nothumansearch.ai
Docs: none
Support: none
Icon: none
Remote endpoint: https://nothumansearch.ai/mcp
Server card: none

Use-case taxonomy

Transport compliance drilldown

Probe status

Not_Assessed

Transport

unknown

Session header

Protocol header

Bad protocol response

n/a

DELETE teardown

n/a

Expired session retry

n/a

Last-Event-ID visible

Issues: none

Request association

Status

Not_Assessed

Advertised capabilities

none

Observed idle methods

none

Violating methods

none

Probe HTTP status

n/a

Issues

none

Connector replay

Status

Not_Assessed

Backward compatible

Would break after refresh

Added tools

none

Removed tools

none

Additive output changes

none

Required-argument replay breaks

Tool	Added required args	Removed required args
No required-argument replay breaks detected.

Output-schema replay breaks

Tool	Removed properties	Added properties
No output-schema replay breaks detected.