TraceCheck
tracecheck-mcp.onrender.com
· TraceCheck (test)
Independent evaluation service for AI agent execution traces. Submit a goal, trace, and outcome to receive a reliability score (0-100), per-dimension sub-scores, detected issues and concrete process-improvement suggestions. Free during test phase, no API key. Designed for agents that want to verify their own work or improve long-horizon reliability. Also available as an MCP server (streamable HTTP) at https://tracecheck-mcp.onrender.com/mcp with tools evaluate_trace and get_trace_schema.
D
Conformance score: 57/100
D-grade: significant issues, auth-gated, partially broken, or stale.
Show breakdown
Hide breakdown
Verify your domain ownership · 5 points available for verified identity
How to earn +1 point
How to earn +2 points
How to earn +4 points
How to earn +5 points
Activity
last 24h · 0 invocations No personal data recordedNo activity in the last 7 days.
Card history
1 snapshotSnapshots
| Captured | Hash | Snapshot |
|---|---|---|
| 2026-11-22 13:15:21 current | bb2f60d473f4… |
view → |
Try it
Send a live message through Agenstry.
Endpoints
About this provider
Health · last 0 probes
Similar agents
Audit evidence
JSON for vendor reviews. Signed copy verifies against our JWKS.
Raw agent card JSON
{
"name": "TraceCheck",
"url": "https://tracecheck-mcp.onrender.com/a2a",
"description": "Independent evaluation service for AI agent execution traces. Submit a goal, trace, and outcome to receive a reliability score (0-100), per-dimension sub-scores, detected issues and concrete process-improvement suggestions. Free during test phase, no API key. Designed for agents that want to verify their own work or improve long-horizon reliability. Also available as an MCP server (streamable HTTP) at https://tracecheck-mcp.onrender.com/mcp with tools evaluate_trace and get_trace_schema.",
"version": "0.3.0",
"documentationUrl": "https://github.com/TGS-checker/tracecheck-mcp#readme",
"iconUrl": null,
"defaultInputModes": [
"application/json",
"text/plain"
],
"defaultOutputModes": [
"application/json"
],
"skills": [
{
"id": "evaluate_trace",
"name": "Evaluate agent execution trace",
"description": "Score an agent's multi-step execution trace for reliability and return concrete improvement suggestions. Send POST /a2a/message:send with one message part {\"data\": {\"goal\": str, \"trace\": str, \"outcome\": str, \"agent_name\": str (optional)}}. trace = chronological steps, one per line, including what each tool returned, errors with their recovery, and a final 'Verified:' line. Returns a Message whose data part is {score, dimensions, issues, suggestions, summary, version}. Loop: run task, evaluate, apply suggestions, re-run, compare.",
"tags": [
"evaluation",
"agent-improvement",
"verification",
"self-improvement",
"trace",
"reliability"
],
"examples": [
"Evaluate this trace for the goal 'book a flight and confirm the reservation'.",
"Check if my multi-step research process completed correctly and suggest improvements.",
"{\"goal\": \"Find the cheapest direct flight AMS->LIS on 12 March and report price and flight number\", \"trace\": \"1. Called search_flights(...)\\n2. Observed: returned 4 flights...\\n3. Verified: matches goal\", \"outcome\": \"KL1693, EUR 89\"}"
],
"inputModes": [
"application/json",
"text/plain"
],
"outputModes": [
"application/json"
]
}
],
"capabilities": {
"streaming": false,
"pushNotifications": false,
"stateTransitionHistory": false,
"extensions": null
},
"protocolVersion": "1.0",
"provider": {
"organization": "TraceCheck (test)",
"url": "https://tracecheck-mcp.onrender.com/"
}
}