TraceCheck
Server Details
Scores an AI agent's execution trace 0-100 and returns concrete fixes. Free, no API key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- TGS-checker/tracecheck-mcp
- GitHub Stars
- 0
- Server Listing
- Tracecheck
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools serve clearly separate purposes: evaluate_trace performs the scoring, while get_trace_schema only returns format documentation and is explicitly 'call once before your first evaluate_trace'. Descriptions even cross-reference each other, so an agent cannot mistake which to call for which need.
Both names use a strict snake_case verb_noun pattern (evaluate_trace, get_trace_schema) with the shared resource token 'trace'. No camelCase or stylistic drift.
Two tools is at the thin end of the scale, and one is purely a documentation helper, leaving a single functional operation. That is defensible for a narrow, single-purpose checker, but the surface feels minimal rather than well-rounded.
The evaluation lifecycle is essentially covered: learn the format via get_trace_schema, then submit goal/trace/outcome for a scored report with issues and suggestions. Minor gaps exist around history/comparison between runs and batch traces, which the 'THE LOOP' guidance implies but no tool supports.
Available Tools
2 toolsevaluate_traceAInspect
Get an independent, deterministic reliability check of a multi-step task you (an agent) just ran. Returns a 0-100 score, the issues found, and concrete fixes to apply on your next attempt.
WHEN TO CALL: after you finish (or give up on) a multi-step task that used tools, before you report "done" to the user, or after a failure you want to learn from. Free, no API key, fast and offline (keyword heuristics, no LLM). Call get_trace_schema first if unsure of the format.
INPUT (all plain strings):
goal: the original task, stated specifically (what success looks like). Vague goals under 20 chars are penalised.
trace: your chronological steps, one per line, e.g. "1. Called search_flights(AMS->LIS) -> returned 3 results" / "2. Observed: ..." . Write what each tool RETURNED ("observed", "returned", "result:"), any error and the retry/fallback you used, and a final "Verified: ..." line.
outcome: the concrete final result you claim, and how it meets the goal.
agent_name: optional identifier for yourself (logging only).
RETURNS JSON: score (int 0-100), dimensions {goal_clarity, observability, error_recovery, goal_alignment, efficiency}, issues (list), suggestions (list, max 5), summary, version.
THE LOOP: run task -> evaluate_trace -> apply the suggestions to your process -> re-run -> evaluate_trace again and compare scores/dimensions. Scores below ~60 usually mean missing observations, unrecovered errors, repeated steps (loops), success claimed without evidence, or no verification step.
Inputs: goal (required), trace (required), outcome (required), agent_name.
get_trace_schemaAInspect
Return the exact input format TraceCheck's evaluate_trace expects, the scored dimensions and weights, and a complete example call you can copy. Call this once before your first evaluate_trace. No arguments, no side effects.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent
Lints + auto-fixes how AI coding agents discover any new product. 24 rules, 6 tools, score 0-100.
Scores how well AI agents will use your API, 0-100, from its OpenAPI spec. Free and read-only.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceScores AI agent trajectories and detects silent failures, loops, and reliability issues with zero external API cost.-
- AlicenseAqualityDmaintenanceAnalyzes AI agent traces to diagnose failures, score performance, and provide actionable fixes using tools like judge_trace and trace_breakdown.32MIT

Pisama MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables analysis of AI agent traces to detect and fix failures using heuristic detectors, with no LLM calls required.1MIT- AlicenseAqualityBmaintenanceEnables AI agents to perform one-shot triage of Playwright trace files, pinpointing root causes like backend API failures or locator issues and generating self-healing code fixes in a single low-token call.4MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.