← Back to search
ai.analyticslegends/sap-analytics

Analytics Legends — SAP Analytics Intelligence

AI agent for SAP analytics: firms, day rates, contract radar, news, concepts, studies

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
69.5
Snapshot trustsnap_9a27dfe9b7af5257
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
Low 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 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
69.5
Transport
streamable-http
Tools
10

Current trust snapshot

Snapshot ID
trustsnap_9a27dfe9b7af5257
Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Snapshot generated
Jul 31, 2026 06:58:29 AM UTC
All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.
Last validated
Jul 31, 2026 05:33:58 AM UTC
Age: 1.41h • freshness band: Verified in last 24h • display score: 69.52
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.analyticslegends/sap-analytics/revalidate
Verified owners get priority queueing after proof succeeds.
3. Badge
Verified by MCP Verify badge
Verified by MCP Verify - score 69.5 - 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.analyticslegends/sap-analytics.svg)](https://verify.sentinelsignal.io/servers/ai.analyticslegends/sap-analytics)

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: 53.0 • 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
score_below_hosting_threshold
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 1.4 hours.
Live checks captured
26
More direct checks increase trust in the current verdict.
Validation age
1.4h
Lower age means fresher evidence.

Recommended for

Claude Desktop
Claude Desktop is marked compatible with score 100.
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.
Confidence: high (76.25)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeWarning
  • 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
No major blockers detected.
Confidence: high (76.25)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeWarning
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.
  • 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
Claude remote MCP
Client-compatible
Remediation checklist
  • 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
  • Transport compliance issues should be resolved before wider client rollout.
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. 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, discovery, and remote-MCP assumptions are satisfied. 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.
  • remote_http_endpoint: Passes
  • oauth_discovery: Degraded
  • frozen_tool_snapshot_refresh: Passes
  • request_association: Passes
Anthropic remote MCP fixture
Passes
Remote MCP transport and discovery assumptions are satisfied.
  • 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 05:33:58 AM UTC Latest validation: healthy Score 69.5 with status healthy.

Capabilities

Use-case taxonomy
development database search web

Security posture

Tools analyzed
10
High-risk tools
6
Destructive tools
1
Exec tools
6
Egress tools
0
Secret tools
0
Bulk-access tools
6
Risk distribution
low:2, medium:2, high:5, critical: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
39
Auth posture
20
Payment readiness
70
Delegation safety
30
Tool risk
70
Commerce signal: moderate Payment capable: inferred Payment execution: no Billing/usage context: no Quote/pricing context: yes Numeric price context: yes Commercial quote context: yes Checkout/charge signal: no Checkout term observed: no Human confirmation: yes Spending policy: yes Receipt support: unknown Auth required: no Operator identity: declared Tool risk: administrative Delegation level: research only
Detected payment rails
Stripe, card
Purchase stages
none detected
Evidence level
inferred
Confidence
medium

Warnings

Evidence

FieldValueSourceMatched termsConfidence
commerce_signalmoderatetool_schemalimit, currency, quote, rate, cardmedium
payment_railsStripe, cardtool_schemastripe, cardmedium

Recommended operator fixes

Tool capability & risk inventory

ToolCapabilitiesRiskFindingsNotes
search_firms read write exec network filesystem export High command execution bulk data access filesystem mutation No explicit safeguard hints detected.
get_firm read network filesystem Medium none No explicit safeguard hints detected.
list_firm_kinds read filesystem Low none No explicit safeguard hints detected.
find_opportunities read write delete exec network admin export Critical destructive operation command execution bulk data access admin mutation No explicit safeguard hints detected.
search_news read exec network filesystem export High command execution bulk data access No explicit safeguard hints detected.
search_concepts read exec export High command execution bulk data access No explicit safeguard hints detected.
get_concept read network Medium none No explicit safeguard hints detected.
list_studies read exec network export High command execution bulk data access No explicit safeguard hints detected.
get_day_rate_benchmark read Low none No explicit safeguard hints detected.
list_sap_modules read exec admin export High command execution bulk data access No explicit safeguard hints detected.

Write-action governance

Governance status
Error
Safe to publish
Auth boundary
public_or_unclear
Blast radius
High
High-risk tools
6
Confirmation signals
none
Safeguard count
0

Status detail: 6 high-risk tool(s), 1 destructive tool(s), 6 exec-capable tool(s) are exposed without a clear auth boundary; no safeguards or confirmation signals detected.

ToolRiskFlagsSafeguards
search_firms High command execution bulk data access filesystem mutation no
find_opportunities Critical destructive operation command execution bulk data access admin mutation no
search_news High command execution bulk data access no
search_concepts High command execution bulk data access no
list_studies High command execution bulk data access no
list_sap_modules 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
31/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
38/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
22/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
17.75/24
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
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
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
3/4
Availability, latency, and burst-failure profile across recent validation history.
Security Hygiene
3/4
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
3/4
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
3/4
Determinism and state behavior across repeated MCP calls, including sticky-session surprises.
Tool Surface Design
4/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
3/4
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
2/4
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
4/4
How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.
Destructive Operation Safety
2/4
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
0/4
Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.
Data Exfiltration Resilience
3/4
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
77.8
partial
OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.
Connector URL: https://analyticslegends.ai/mcp
# No OAuth metadata detected.
# Server: ai.analyticslegends/sap-analytics
Claude Desktop
100.0
compatible
No major blockers detected.
{
  "mcpServers": {
    "sap-analytics": {
      "command": "npx",
      "args": ["mcp-remote", "https://analyticslegends.ai/mcp"]
    }
  }
}
Smithery
80.0
compatible
Machine-readable failure semantics should be present.
smithery mcp add "https://analyticslegends.ai/mcp"
Generic Streamable HTTP
100.0
compatible
No major blockers detected.
curl -sS https://analyticslegends.ai/mcp -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 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.

Point loss breakdown

ComponentCurrentPoints missing
Recovery Semantics 0/4 -4.0
Execution Sandbox Safety 0/4 -4.0
Error Contract 0/4 -4.0
Trust Confidence 1.8/4 -2.2
Utility Coverage 2/4 -2.0
Transport Compliance 2/4 -2.0
Spec Recency 2/4 -2.0
Safety Transparency 2/4 -2.0
Registry Consistency 2/4 -2.0
Rate Limit Semantics 2/4 -2.0
Least Privilege Scope 2/4 -2.0
Destructive Operation 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
Warning
Transport
streamable-http
Session header
no
Protocol header
yes
Bad protocol response
400
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no

Issues: missing_session_id

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: { "argument_name": "country", "name": "brief_sap_analytics_market", "type": "prompt" }
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.analyticslegends/sap-analytics official_registry yes 69.52

Alias consolidation

Canonical identifier
ai.analyticslegends/sap-analytics
Duplicate aliases
0
Registry sources
official_registry
Source disagreements
FieldWhat differsObserved values
No source disagreements detected.

Install snippets

Openai Connectors
Connector URL: https://analyticslegends.ai/mcp
# No OAuth metadata detected.
# Server: ai.analyticslegends/sap-analytics
Claude Desktop
{
  "mcpServers": {
    "sap-analytics": {
      "command": "npx",
      "args": ["mcp-remote", "https://analyticslegends.ai/mcp"]
    }
  }
}
Smithery
smithery mcp add "https://analyticslegends.ai/mcp"
Generic Http
curl -sS https://analyticslegends.ai/mcp -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
search_firms get_firm list_firm_kinds find_opportunities search_news search_concepts get_concept list_studies
Observed from the latest live validation against https://analyticslegends.ai/mcp. This is the target server surface, not Verify's own inspection tools.
Live capability counts
10 tools • 2 prompts • 3 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.analyticslegends/sap-analytics.
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
5167.1
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, web
Score Trend
69.52
Remediation Count
15
High Risk Tool Count
6
Destructive Tool Count
1
Exec Tool Count
6

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 05:33:52 AM UTC
Latency
5167.1 ms

Failures

Checks

CheckStatusLatencyEvidence
action_safety_probe Error n/a 6 high-risk, 1 destructive, 6 exec-capable tool(s); no clear auth boundary; safeguards=0; confirmation=none.
advanced_capabilities_probe OK n/a 4 capability signal(s): prompts, resource links, resources, structured outputs.
connector_publishability_probe Warning n/a Publishability blockers: action safety, server card.
connector_replay_probe Missing n/a No connector replay evidence recorded.
determinism_probe OK 110.3 ms Check completed
initialize OK 177.1 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 49.3 ms Client error '404 Not Found' for url 'https://analyticslegends.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 39.3 ms Fetched https://analyticslegends.ai/robots.txt
prompt_get OK 109.8 ms 1 prompt message(s) returned
prompts_list OK 121.5 ms 2 prompt(s) exposed
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 3826.1 ms 1 resource content item(s) returned
resources_list OK 127.8 ms 3 resource item(s) exposed
server_card Error 185.3 ms Client error '404 Not Found' for url 'https://analyticslegends.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 96.7 ms 10 tool(s) exposed
transport_compliance_probe Warning 111.7 ms Issues: missing session id (bad protocol=400).
utility_coverage_probe Missing 93.0 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": 0,
        "summary": {
          "bulk_access_tools": 6,
          "capability_distribution": {
            "admin": 2,
            "delete": 1,
            "exec": 6,
            "export": 6,
            "filesystem": 4,
            "network": 6,
            "read": 10,
            "write": 2
          },
          "destructive_tools": 1,
          "egress_tools": 0,
          "exec_tools": 6,
          "high_risk_tools": 6,
          "risk_distribution": {
            "critical": 1,
            "high": 5,
            "low": 2,
            "medium": 2
          },
          "secret_tools": 0,
          "tool_count": 10
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": true,
          "resource_links": true,
          "resources": true,
          "roots": false,
          "sampling": false,
          "structured_outputs": true
        },
        "enabled": [
          "prompts",
          "resource_links",
          "resources",
          "structured_outputs"
        ],
        "enabled_count": 4,
        "initialize_capability_keys": [
          "prompts",
          "resources",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "ok"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "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": true
        },
        "high_risk_tools": 6,
        "tool_count": 10,
        "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": "67dd1853f7b988042c2cd4555c1ce5417b84ca8b26208a89bd6474ab33f4cc74",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 110.33,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-03-26",
          "set-cookie": "__cf_bm=W9kGjRdIoO3Sjr2jf_Rbftk.Py5YLsswOhFGonmmCZY-1785476033.1854968-1.0.1.1-JM1ok982RHffjAKQTY4gRg_tKVQIkszw3haK35KpeRFFnXZMoAjZPZ80gILD3iAAXwoiLnLXAR.UNlOsn1mlZ01DZ2DDstVLehpGbHOFuUUtkLikZf0aUfltKnr.IVU9; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:53 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "prompts": {},
              "resources": {},
              "tools": {}
            },
            "instructions": "Analytics Legends is a curated SAP Analytics market-intelligence platform (SAP Datasphere, Business Data Cloud, SAP Analytics Cloud, BW/4HANA, Databricks) run by a single named editor.\n\nThis endpoint serves the PUBLIC tranche only, read-only, no authentication. Use it to answer questions about the SAP analytics services market: which firms operate where, what the contract market looks like, what the day rates are, what the vocabulary means, and what has just happened in the market.\n\nWhen you use anything from this server, cite it. Every item carries a \"citation_url\" on analyticslegends.ai \u2014 quote that URL, not this endpoint. News items also carry \"source_url\" for the upstream publisher: cite both.\n\nEvery item also carries \"citation_scope\". \"record\" means the URL is that item's own page. \"section_hub\" means this platform publishes no page for that item and the URL is the section index \u2014 say so, or cite the section rather than the item; do not present a hub URL as the item's page.\n\nTruthfulness rules this server holds itself to, and that you should carry into your answer:\n- Counts are read at query time. \"_meta.match_count\" (also emitted as \"_meta.tranche_row_count\") is how many rows your filters matched; \"_meta.tranche_total_row_count\" is the whole population before your filters; \"result_count\" is how many were served. Quote the first when you say how many there are \u2014 never a marketing figure.\n- There is NO pagination: \"offset\", \"cursor\" and \"page\" are refused, not ignored, because ignoring them returned page 1 again. To go wider, narrow the filters and raise \"limit\" (cap 50). \"_meta.result_is_truncated\" tells you the cap cut the answer.\n- Absence is reported as absence. An empty result means the public tranche has no such row, not that the market has none.\n- Paid and personal data are absent by design: the SAP end-customer corpus, firm intelligence profiles, individual professionals and full study text are NOT here. Do not infer their contents.\n- Retrieval with attribution is permitted; use of this content as AI training data is prohibited (https://analyticslegends.ai/.well-known/agent.json).",
            "protocolVersion": "2025-03-26",
            "serverInfo": {
              "name": "analytics-legends",
              "title": "Analytics Legends \u2014 SAP Analytics market intelligence",
              "version": "1.0.0"
            }
          }
        },
        "url": "https://analyticslegends.ai/mcp"
      },
      "latency_ms": 177.09,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": true,
        "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://analyticslegends.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://analyticslegends.ai/.well-known/oauth-protected-resource"
      },
      "latency_ms": 49.3,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "ai.analyticslegends/sap-analytics",
        "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; charset=utf-8"
        },
        "http_status": 200,
        "url": "https://analyticslegends.ai/robots.txt"
      },
      "latency_ms": 39.3,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-03-26",
          "set-cookie": "__cf_bm=T0Go4eCr9KHm9tEBtuPklG2cOuJjzzhPfoFB5vkFkus-1785476033.5557928-1.0.1.1-q6R53OK0SRicpZgRx40gOH0jmtyqcZ2Y0OB.HiG5gbqVm.SQ9oV9hI.aOlXc4N3eREoEl0YYtPYeN6fzrD95MFI1GNg1FJA.mS1a31VHudEzXIGk5BpYlBnnZz3TshaH; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:53 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "http_status": 200,
        "payload": {
          "id": 4,
          "jsonrpc": "2.0",
          "result": {
            "description": "Sourced SAP analytics market briefing for DE.",
            "messages": [
              {
                "content": {
                  "text": "Brief me on the SAP analytics services market in DE.\n\nUse the analytics-legends tools in this order and cite every claim:\n1. list_firm_kinds \u2014 establish the population before naming anyone.\n2. search_firms with country=\"DE\" \u2014 who provides these services there.\n3. find_opportunities with country=\"DE\" \u2014 what the demand side is asking for right now.\n4. get_day_rate_benchmark with country=\"DE\" \u2014 the public rate band; quote sample_size with it.\n5. search_news \u2014 what has just changed.\n\nRules: quote each item's citation_url. For news, quote source_url too. Report the tranche_row_count you searched, and say plainly when a result set is empty rather than filling the gap from memory. Do not state day-rate quartiles \u2014 they are not public.",
                  "type": "text"
                },
                "role": "user"
              }
            ]
          }
        },
        "prompt_arguments": [
          {
            "description": "ISO-3166 alpha-2 country code, e.g. DE.",
            "name": "country",
            "required": true
          },
          {
            "description": "Optional product focus, e.g. Datasphere, BDC, SAC.",
            "name": "focus",
            "required": false
          }
        ],
        "prompt_name": "brief_sap_analytics_market",
        "url": "https://analyticslegends.ai/mcp"
      },
      "latency_ms": 109.78,
      "status": "ok"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-03-26",
          "set-cookie": "__cf_bm=IgiDwEUlD1mhmRpYYwsrW04wHGnu4zpNUImhIubbRoU-1785476033.434199-1.0.1.1-h8393WbuHNdFU_pot_1iRh768wo44hS8pyIt1Xv9kOv.jY9iAAO9Gh80sUS19c2zVTJhsHJFt5d2WcajvQJODYdXaSnguTDcTnf_u.gLedIx5.wKwswy3Xphe1RfvcXi; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:53 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "http_status": 200,
        "payload": {
          "id": 3,
          "jsonrpc": "2.0",
          "result": {
            "prompts": [
              {
                "arguments": [
                  {
                    "description": "ISO-3166 alpha-2 country code, e.g. DE.",
                    "name": "country",
                    "required": true
                  },
                  {
                    "description": "Optional product focus, e.g. Datasphere, BDC, SAC.",
                    "name": "focus",
                    "required": false
                  }
                ],
                "description": "Assemble a sourced, cited briefing on the SAP analytics services market for one country: who the providers are, what is on the radar, what the day rates look like and what has just happened.",
                "name": "brief_sap_analytics_market",
                "title": "Brief me on the SAP analytics market in a country"
              },
              {
                "arguments": [
                  {
                    "description": "The term to explain.",
                    "name": "term",
                    "required": true
                  }
                ],
                "description": "Explain one SAP analytics term from the Analytics Legends encyclopaedia and cite the canonical URL.",
                "name": "explain_sap_analytics_term",
                "title": "Explain an SAP analytics term with a citation"
              }
            ]
          }
        },
        "url": "https://analyticslegends.ai/mcp"
      },
      "latency_ms": 121.47,
      "status": "ok"
    },
    "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": "2025-03-26",
          "set-cookie": "__cf_bm=AhVFf_HPoF5ffRfVeBnMxX8Eorvj.aTO3v.p8G5rLWc-1785476033.7936084-1.0.1.1-5.alWTTmrez.6zkfNPCM9fVsE_JNSuj9XI1MJA7ZR0iYjZjnyLLGxfjlDv3CPH0eO4YRZnc4ES9eZZh3vKLMo.2p8G8W7O_U1pAtcV2rYCt_qb8ODGQEkQYfv1_.todK; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:57 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "http_status": 200,
        "payload": {
          "id": 6,
          "jsonrpc": "2.0",
          "result": {
            "contents": [
              {
                "mimeType": "application/json",
                "text": "{\n  \"endpoint\": \"https://analyticslegends.ai/mcp\",\n  \"auth\": \"none \u2014 public read-only tranche\",\n  \"served\": {\n    \"firms\": {\n      \"source\": \"database.organizations\",\n      \"rows\": 5048,\n      \"tools\": [\n        \"search_firms\",\n        \"get_firm\",\n        \"list_firm_kinds\"\n      ]\n    },\n    \"opportunities\": {\n      \"source\": \"public.public_opportunities + https://analyticslegends.ai/api/contracts-lean.json (all active rows; the application link alone is tier-gated)\",\n      \"rows\": 19,\n      \"rows_note\": \"`rows` counts the promoted leg only; the site-radar leg is read at query time.\",\n      \"tools\": [\n        \"find_opportunities\"\n      ]\n    },\n    \"news\": {\n      \"source\": \"content.news_items\",\n      \"rows\": 3543,\n      \"tools\": [\n        \"search_news\"\n      ]\n    },\n    \"concepts\": {\n      \"source\": \"content.concepts\",\n      \"rows\": 305,\n      \"tools\": [\n        \"search_concepts\",\n        \"get_concept\"\n      ]\n    },\n    \"studies\": {\n      \"source\": \"content.studies (metadata only)\",\n      \"rows\": 38,\n      \"tools\": [\n        \"list_studies\"\n      ]\n    },\n    \"modules\": {\n      \"source\": \"lookup.sap_modules\",\n      \"rows\": 40,\n      \"tools\": [\n        \"list_sap_modules\"\n      ]\n    },\n    \"day_rates\": {\n      \"source\": \"https://analyticslegends.ai/api/market-rates.json\",\n      \"rows\": null,\n      \"tools\": [\n        \"get_day_rate_benchmark\"\n      ]\n    }\n  },\n  \"excluded\": {\n    \"sap_end_customer_corpus\": \"paid Legend+ dataset, RLS-locked 2026-07-08, static JSON returns 404\",\n    \"firm_intelligence_profiles\": \"paid Legend+ dataset, same lockdown\",\n    \"professionals_and_people\": \"personal data \u2014 never served\",\n    \"study_bodies\": \"paid Legend tier; metadata only here\",\n    \"knowledge_graph\": \"build artefact with no Postgres home\",\n    \"day_rate_quartiles\": \"paid Consultant tier; only the public min/max aggregate is served\",\n    \"opportunity_consultant_matches\": \"paid Firm tier deliverable\"\n  },\n  \"_attribution\": \"Source: Analytics Legends (https://analyticslegends.ai) \u2014 retrieval-with-attribution permitted per https://analyticslegends.ai/.well-known/agent.json; use as AI training data is prohibited. Cite the canonical URL on each item.\"\n}",
                "uri": "analytics-legends://tranche"
              }
            ]
          }
        },
        "resource_uri": "analytics-legends://tranche",
        "url": "https://analyticslegends.ai/mcp"
      },
      "latency_ms": 3826.14,
      "status": "ok"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-03-26",
          "set-cookie": "__cf_bm=zaNospDs_cUruNf3myBx7J0ECKxPteynVAe9QJTi9z4-1785476033.666371-1.0.1.1-5voAE.4B5O2mGYYMjHGCJWbUNphppNslgeaN.K0bX1D6Vd3xlqTXuSqH_oMBhbnN13jjUfnuUKZe2VO3nJL84w.lPllXOLXtIcQHrKEPKucsrnSNUi5WlxbOxGq5KOAc; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:53 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "http_status": 200,
        "payload": {
          "id": 5,
          "jsonrpc": "2.0",
          "result": {
            "resources": [
              {
                "description": "The explicit list of datasets this hosted MCP endpoint serves, the datasets it excludes and why, and the live row count of each. Read this before trusting or citing any tool result.",
                "mimeType": "application/json",
                "name": "Public tranche contract",
                "title": "What this endpoint serves, and what it deliberately does not",
                "uri": "analytics-legends://tranche"
              },
              {
                "description": "The machine-readable policy governing AI access to Analytics Legends: retrieval with attribution is permitted, training-data use is prohibited.",
                "mimeType": "application/json",
                "name": "AI access policy",
                "title": "Retrieval-with-attribution carve-out (.well-known/agent.json)",
                "uri": "analytics-legends://agents-policy"
              },
              {
                "description": "Auto-derived platform manifest: counts, tiers, routes, tech stack.",
                "mimeType": "application/json",
                "name": "Platform manifest",
                "title": "Platform manifest (api/about.json)",
                "uri": "analytics-legends://about"
              }
            ]
          }
        },
        "url": "https://analyticslegends.ai/mcp"
      },
      "latency_ms": 127.77,
      "status": "ok"
    },
    "server_card": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://analyticslegends.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://analyticslegends.ai/.well-known/mcp/server-card.json"
      },
      "latency_ms": 185.3,
      "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": 10,
        "reason": "no_historical_snapshot"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-protocol-version": "2025-03-26",
          "set-cookie": "__cf_bm=7L5A0pM_ije_aAtUJyaF_D_t79djjj5Fr_FZhvsPo1M-1785476033.337834-1.0.1.1-LqD3gkhAMsnwm9Rw2NA3d9US2gCZjk12H0YMR0geyFj.5Ri14pCkE9sC8nHN5QrUS_FLRN1brzNC9CZxB16aCm06FFZldlSIbTERcAGTqq3uaviSXqj6suRYEijLANvx; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:53 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search the SAP analytics firm directory"
                },
                "description": "Search the published Analytics Legends directory of SAP analytics service providers \u2014 placement agencies, Big-4 and ESN practices, SAP vendors, platforms and community groups \u2014 by country, kind and free text. Returns name, HQ country/city, website, careers URL and a one-line editorial claim. SAP END-CUSTOMER companies are NOT in this directory: they are a separate paid dataset and are excluded by predicate.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "country": {
                      "description": "ISO-3166-1 alpha-2 country code, e.g. DE, FR, CH.",
                      "pattern": "^[A-Za-z]{2}$",
                      "type": "string"
                    },
                    "kind": {
                      "description": "Restrict to one organisation kind. Call list_firm_kinds for live counts. A value outside this list is refused, not silently ignored.",
                      "enum": [
                        "agency_placement",
                        "professional_services_big4",
                        "professional_services_esn",
                        "vendor_sap",
                        "vendor_partner",
                        "platform_marketplace",
                        "community_group"
                      ],
                      "type": "string"
                    },
                    "limit": {
                      "default": 10,
                      "description": "Max rows (hard cap 50).",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Free-text filter, matched case-insensitively.",
                      "maxLength": 200,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "search_firms",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "hq_country": {
                            "type": "string"
                          },
                          "kind": {
                            "type": "string"
                          },
                          "name": {
                            "type": "string"
                          },
                          "slug": {
                            "type": "string"
                          },
                          "website": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Search the SAP analytics firm directory"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get one firm's published profile"
                },
                "description": "Fetch one organisation from the published directory by its database slug (`rows[].slug` from search_firms, verbatim). Returns the same public fields plus `partnerships_declared`, the count of partnerships this directory records for the firm \u2014 0 on ~94 % of rows, meaning none declared here, never that the firm has no partners. Does not return the paid firm-intelligence profile, contacts, or any person.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "slug": {
                      "description": "The DATABASE slug, taken verbatim from search_firms.rows[].slug. It is not always the web slug in citation_url: re-measured 2026-07-31 against the tranche this tool actually serves (5 157 published rows), 429 of them (8,3 %) carry a numeric firm id instead \u2014 '00317' is BearingPoint Switzerland, whose page is /companies/bearingpoint-switzerland/. Deriving a slug from the citation URL fails on those rows; carry rows[].slug across instead.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "slug"
                  ],
                  "type": "object"
                },
                "name": "get_firm",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "name": {
                            "type": "string"
                          },
                          "slug": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Get one firm's published profile"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "List firm kinds with live counts"
                },
                "description": "Breakdown of the published firm directory by organisation kind, with a live row count per kind. Use this before search_firms to know what the population actually is instead of guessing.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {},
                  "type": "object"
                },
                "name": "list_firm_kinds",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "kind": {
                            "type": "string"
                          },
                          "n": {
                            "type": "integer"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "List firm kinds with live counts"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search the public SAP analytics contract radar"
                },
                "description": "Search every SAP contract and permanent-role posting Analytics Legends publishes to an ANONYMOUS visitor \u2014 the same population a human browses on /opportunities/, where each posting has its own prerendered page. It merges the platform's TWO public legs, which are near-disjoint (measured 2026-07-30: 1 row in common): (a) the PROMOTED feed (`public.public_opportunities`) \u2014 general SAP work (FI/CO, SD, EWM, MDG, BTP, ABAP), all German cities, and it carries NO rate, contract_type, currency, posted_at or country_code: those fields come back null on that leg, so no rate or contract term can be read off it; (b) the SITE RADAR (`/api/contracts-lean.json`) \u2014 these DO carry country, category, seniority, posted_at and currency, and they are the analytics-specific ones (SAC Planning, Datasphere Technical Lead, Business Data Cloud). WHAT IS GATED IS A FIELD, NOT A ROW: on most radar rows `source_url` is null and `application_link` reads \"members_only\" \u2014 the verified link to the original listing is the paid Consultant-tier deliverable. Everything else about the posting is public, and `citation_url` is that posting's own page on analyticslegends.ai. Quote it. Report `_meta.tranche_row_count` as the published public population, never as the size of the market.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "country": {
                      "description": "ISO-3166-1 alpha-2 code. It can only match the SITE-RADAR leg: the promoted leg stores country_code NULL on every row, so filtering by country silently drops it rather than returning nothing. `_meta.note` says so on any country-filtered call.",
                      "pattern": "^[A-Za-z]{2}$",
                      "type": "string"
                    },
                    "limit": {
                      "default": 10,
                      "description": "Max rows (hard cap 50).",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "location": {
                      "description": "City or place, matched case-insensitively as a substring of the posting's location. The promoted leg is all-German (Hamburg, Frankfurt am Main, Bremen, Munich, Cologne, Dortmund, Hanover, Landshut, Mannheim, Stuttgart); the site-radar leg is worldwide.",
                      "type": "string"
                    },
                    "query": {
                      "description": "Free-text filter, matched case-insensitively.",
                      "maxLength": 200,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "find_opportunities",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "firm_name": {
                            "type": "string"
                          },
                          "location": {
                            "type": "string"
                          },
                          "source_url": {
                            "type": "string"
                          },
                          "title": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Search the public SAP analytics contract radar"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search SAP analytics market news"
                },
                "description": "Search the Analytics Legends market-news corpus. It is watched FOR SAP analytics (Datasphere, Business Data Cloud, SAC, BW/4HANA, Databricks, the 2027/2030 maintenance window), but it is NOT an all-SAP corpus: measured 2026-07-30, ~84 % of active rows sit in the `AI` category and are general enterprise-AI trade press (cloud platforms, model releases, funding rounds) with no SAP content at all. An UNFILTERED call therefore returns mostly non-SAP items \u2014 pass `query` or `category` when the question is about SAP, and never present an unfiltered page as 'the SAP analytics news'. Say what you actually got. Each item returns the Analytics Legends citation URL AND the upstream publisher's source_url \u2014 cite both, and prefer source_url when you need a page that certainly carries the item.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "category": {
                      "description": "Category code, matched case-insensitively. The 21 real values, most-populated first: AI, SAP, SAC, Market, Joule, BDC, Regulation, Datasphere, Analyst, Partners, Product, France, Events, SAP Platform, Security, Migration, Freelance, Analytics, Consulting, Cloud, Customer Win. Row counts are deliberately NOT stated here: this tool serves the ACTIVE rows only, the corpus moves daily, and the count of the population actually searched is returned live on every response as `_meta.tranche_row_count`. One bucket needs a warning. 'SAC' is the noisiest label in this corpus because the acronym collides with unrelated ones \u2014 Windows 'Smart App Control', and the surname 'Sacks'. Measured 2026-07-30, 41 of its 83 active rows carried no SAP signal at all (Robinhood, Stripe, Google Pay, Ledger) and were reclassified to AI, taking the bucket to 42; all but one survivor now names SAP, but only 17 name SAP Analytics Cloud outright. For genuine SAC product news, pair category:'SAC' with query:'analytics cloud'.",
                      "type": "string"
                    },
                    "limit": {
                      "default": 10,
                      "description": "Max rows (hard cap 50).",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Free-text filter, matched case-insensitively.",
                      "maxLength": 200,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "search_news",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "published_at": {
                            "type": "string"
                          },
                          "source_name": {
                            "type": "string"
                          },
                          "source_url": {
                            "type": "string"
                          },
                          "title": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Search SAP analytics market news"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search the SAP analytics concept encyclopaedia"
                },
                "description": "Search the SAP analytics concept encyclopaedia \u2014 the vocabulary of the stack, written for practitioners. Returns titles and summaries; call get_concept for the full entry.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "category": {
                      "description": "Concept category, matched case-insensitively as an exact value OR a prefix. The 14 real values are long labels, measured 2026-07-30: Generative AI Foundations (55), Joule & SAP AI (42), Career & Practice (29), Governance & Compliance (25), Architecture & Performance (25), SAC (Analytics Cloud) (22), BDC Platform (22), Adjacent Stacks (19), Datasphere Core (17), Sales & Commercial (16), Productivity & AI (10), Industry Solutions (10), BW/4HANA & Migration (9), Data Engineering & Integration (1). So category:\"datasphere\" reaches Datasphere Core.",
                      "type": "string"
                    },
                    "limit": {
                      "default": 10,
                      "description": "Max rows (hard cap 50).",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Free-text filter, matched case-insensitively.",
                      "maxLength": 200,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "search_concepts",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "slug": {
                            "type": "string"
                          },
                          "title": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Search the SAP analytics concept encyclopaedia"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get one concept entry in full"
                },
                "description": "Fetch one concept entry by slug: title, category, level, tags and the editor's summary. Written by a named human editor, not generated. The card body, why-it-matters, key points and pro tip are subscriber content and are NOT returned \u2014 follow citation_url for those.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "slug": {
                      "description": "Concept slug from search_concepts.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "slug"
                  ],
                  "type": "object"
                },
                "name": "get_concept",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "slug": {
                            "type": "string"
                          },
                          "summary": {
                            "type": "string"
                          },
                          "title": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Get one concept entry in full"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "List the deep-research studies (metadata only)"
                },
                "description": "List the Analytics Legends deep-research studies with their edition, as-of date, audience, word count and canonical URL. METADATA ONLY: study bodies are a paid Legend-tier deliverable and are not served by this endpoint. Use this to tell a reader that a study exists and where to read it.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "lang": {
                      "description": "Language code, EN or FR.",
                      "pattern": "^[A-Za-z]{2}$",
                      "type": "string"
                    },
                    "limit": {
                      "default": 10,
                      "description": "Max rows (hard cap 50).",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Free-text filter, matched case-insensitively.",
                      "maxLength": 200,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "list_studies",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "access": {
                            "type": "string"
                          },
                          "as_of": {
                            "type": "string"
                          },
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "slug": {
                            "type": "string"
                          },
                          "title": {
                            "type": "string"
                          },
                          "word_count": {
                            "type": "integer"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "List the deep-research studies (metadata only)"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Public SAP analytics day-rate aggregate"
                },
                "description": "The PUBLIC day-rate aggregate for SAP analytics freelance work: min/max daily rate by country, specialisation and seniority, with a sample size and a quarter stamp. This is the free aggregate published at analyticslegends.ai/api/market-rates.json. The quartile bands (p25/p50/p75) are a paid Consultant-tier deliverable and are NOT in this response \u2014 do not infer them.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "country": {
                      "description": "ISO-3166-1 alpha-2 country code, e.g. DE, FR, CH.",
                      "pattern": "^[A-Za-z]{2}$",
                      "type": "string"
                    },
                    "seniority": {
                      "description": "e.g. senior, principal.",
                      "type": "string"
                    },
                    "specialisation": {
                      "description": "e.g. datasphere, bdc, sac, bw4hana, joule.",
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "get_day_rate_benchmark",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "country": {
                            "type": "string"
                          },
                          "currency": {
                            "type": "string"
                          },
                          "sample_size": {
                            "type": "integer"
                          },
                          "seniority": {
                            "type": "string"
                          },
                          "specialisation": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "Public SAP analytics day-rate aggregate"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "SAP analytics module taxonomy"
                },
                "description": "The canonical SAP module/product taxonomy Analytics Legends classifies against (codes and EN/FR labels by category). Use it to normalise a user's loose product wording \u2014 'SAC', 'Analytics Cloud', 'Datasphere' \u2014 onto the codes the other tools filter on.",
                "inputSchema": {
                  "additionalProperties": false,
                  "properties": {
                    "limit": {
                      "default": 10,
                      "description": "Max rows (hard cap 50).",
                      "maximum": 50,
                      "minimum": 1,
                      "type": "integer"
                    },
                    "query": {
                      "description": "Free-text filter, matched case-insensitively.",
                      "maxLength": 200,
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "list_sap_modules",
                "outputSchema": {
                  "properties": {
                    "_attribution": {
                      "type": "string"
                    },
                    "_meta": {
                      "type": "object"
                    },
                    "result_count": {
                      "type": "integer"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "category": {
                            "type": "string"
                          },
                          "citation_note": {
                            "type": "string"
                          },
                          "citation_scope": {
                            "enum": [
                              "record",
                              "section_hub"
                            ],
                            "type": "string"
                          },
                          "citation_url": {
                            "type": "string"
                          },
                          "code": {
                            "type": "string"
                          },
                          "label_en": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "tool": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "tool",
                    "result_count",
                    "rows",
                    "_attribution"
                  ],
                  "type": "object"
                },
                "title": "SAP analytics module taxonomy"
              }
            ]
          }
        },
        "url": "https://analyticslegends.ai/mcp"
      },
      "latency_ms": 96.69,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json",
          "set-cookie": "__cf_bm=3kDnPGh4jCY7KMG34yi5GFOmNwwEMxvGn8CZvnHN5f0-1785476037.8862312-1.0.1.1-0hVrQvj6sx6DuAyA1MAhSAn9nHREF.XbaZ0gLHj2AtqFTheHlEQWTGuTVB6QY30PWflwBs.cjJu2.qAWN62rWgkkZexJXUumx07d.qA79PYkRj2ZSfAlRSS0cC47m15M; HttpOnly; SameSite=None; Secure; Path=/; Domain=supabase.co; Expires=Fri, 31 Jul 2026 06:03:57 GMT",
          "strict-transport-security": "max-age=31536000; includeSubDomains; preload"
        },
        "bad_protocol_payload": {
          "error": {
            "code": -32022,
            "data": {
              "requested": "1999-99-99",
              "supported": [
                "2026-07-28",
                "2025-11-25",
                "2025-06-18",
                "2025-03-26"
              ]
            },
            "message": "Unsupported protocol version"
          },
          "id": 410,
          "jsonrpc": "2.0"
        },
        "bad_protocol_status_code": 400,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": true,
        "requested_protocol_version": "2025-03-26",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 111.69,
      "status": "warning"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": {
            "argument_name": "country",
            "name": "brief_sap_analytics_market",
            "type": "prompt"
          }
        },
        "initialize_capability_keys": [
          "prompts",
          "resources",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 404,
          "probe_status": "missing"
        }
      },
      "latency_ms": 93.0,
      "status": "missing"
    }
  },
  "failures": {
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Client error '404 Not Found' for url 'https://analyticslegends.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://analyticslegends.ai/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Client error '404 Not Found' for url 'https://analyticslegends.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://analyticslegends.ai/.well-known/mcp/server-card.json"
    }
  },
  "remote_url": "https://analyticslegends.ai/mcp",
  "server_card_payload": null,
  "server_identifier": "ai.analyticslegends/sap-analytics"
}

Known versions

Validation history

7 day score delta
n/a
30 day score delta
n/a
Recent healthy ratio
100%
Freshness
1.4h
TimestampStatusScoreLatencyTools
Jul 31, 2026 05:33:58 AM UTC Healthy 69.5 5167.1 ms 10

Validation timeline

ValidatedSummaryScoreProtocolAuth modeToolsHigh-risk toolsChanges
Jul 31, 2026 05:33:58 AM UTC Healthy 69.5 2025-03-26 public 10 6 none

Recent validation runs

StartedStatusSummaryLatencyChecks
Jul 31, 2026 05:33:52 AM UTC Completed Healthy 5167.1 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