agiscorecard-web3-evidence
Server Details
Review agent task evidence with sample deduplication, version filters and uncertainty intervals.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 58.3% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- f-tiger/agi-site
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The three tools have distinct core actions: search finds items, fetch retrieves a reference by ID, and review_agent_evidence analyzes imported outcomes. However, fetch is a generic name and the review tool's description mentions retrieving evidence with fetch, which slightly blurs boundaries.
Names use snake_case throughout, but the pattern is mixed: fetch and search are single verbs, while review_agent_evidence follows a verb_noun structure. This is readable but not a predictable convention.
Three tools is within the recommended 3-15 range and each earns its place for a focused public reference server: search, fetch, and review cover distinct retrieval and analysis needs.
The server covers search, retrieval of tool references, and evidence review, but there is no clear tool to retrieve the imported task outcomes that review_agent_evidence needs. Fetch is scoped to tool references, leaving a notable gap in the evidence lifecycle.
Available Tools
3 toolsfetchRead a Web3 method and sourcesARead-onlyIdempotentInspect
Retrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.
Inputs: id (required). Returns: id, url, text, title, +1 more
review_agent_evidenceAgent EvidenceARead-onlyIdempotentInspect
Agent Evidence reviews imported task outcomes within one task, version and date window. It deduplicates sample labels and shows failures, exclusions and uncertainty. It helps review a supplier comparison; it does not run evaluations or verify reviewer identities. No public reputation ranking, identity verification, calibrated prediction or Sybil detection. Retrieve evidence with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Inputs: asOf (required), task (required), records (required), version (required), +1 more. Returns: report, toolId, version, citation, +5 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.
Independent AI-agent reviews: trust checks, evidence scorecards, incident registry, recommendations.
Shared research, saved evidence, independent reviews and open tasks for AI agents.
Evidence infrastructure for agents: source-backed company verification and beta import assessment.
Related MCP Servers
- AlicenseCqualityCmaintenanceEnables agents to validate physical-AI evidence through synthetic scenario and episode reviews, explain beliefs from delayed or conflicting evidence, and audit simulation replays while tracing why a workflow pauses. Pairs local freshness checks with bounded cloud model review and exposes no actuator or arbitrary filesystem tools.5Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to run evidence QC gates mid-workflow—checking claims, sources, prose, and vault hygiene deterministically before research ships.MIT
- AlicenseNot gradedqualityDmaintenanceProvides tools for agents to manage a local review graph, tracking acceptance behaviors, evidence, review passes, and human waivers to decouple review convergence from shipping readiness.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables evidence-first regression testing for AI agents by turning production traces into reviewed, replayable cases that gate releases. It supports reproducible, auditable agent evaluation with controlled tool execution, evidence-based judging, and versioned quality gates.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.