MCP Selection Lab
Benchmark MCP tool selection with metadata-only routing, collision, abstention, and holdout checks.
| Endpoint | https://agenttrustlab.com/mcp (streamable-http) |
|---|---|
| Registry version | 0.5.2 |
| Now | 3 tools · grade A (100) · pin ts_35229940db9cac7cd55f4a9f30d93430 · protocol 2025-06-18 |
| First / last listed | 2026-10-26 07:26 UTC / 2026-10-26 07:26 UTC |
| Grade over time | 2026-10-26: A (100), 3 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: selection_lab_info scan_mcp_metadata get_selection_report
selection_lab_info | Get free service capabilities, limits, privacy and connection details; does not scan a target. params: none |
scan_mcp_metadata | Create a free public report of MCP tool-description routing collisions.
Reads discovery metadata (initialize/tools/list) only; never calls target business
tools or spends funds. Use a public HTTP(S) URL without credentials, query or fragment.
Results use at most 12 tools and 24 generated cases, not a real-model evaluation.
The returned report is enriched with agent_plan candidate params: mcp_url*, source, internal_test |
get_selection_report | Read and agent-enrich an existing public scan report by id; no new target request or model call. params: report_id* |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.