io.github.ChanghuLiu/mcp-selection-lab

repo:https://github.com/changhuliu/mcp-selection-lab

Benchmark MCP tool selection with metadata-only routing, collision, abstention, and holdout checks.

transport:: remote
credential class:: unreachable
repo:: https://github.com/ChanghuLiu/mcp-selection-lab

Owner verification

Not yet verified. Verifying proves you control this server and is free, permanently — it never changes a published score.

Start verification →

Tools

get_selection_report
Read and agent-enrich an existing public scan report by id; no new target request or model call.
shallow
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 description-only edits and a machine-readable rerun instruction. Candidate edits are not untouched-holdout proof. Reports persist and are public by link. For an existing report use get_selection_report. Set internal_test=true for owner/CI validation so it is excluded from public scans. source is a self-reported referral bucket, not identity verification.
shallow
selection_lab_info
Get free service capabilities, limits, privacy and connection details; does not scan a target.
shallow

Embed this server’s score

Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.

[![Vouch score](https://vouch.tools/api/servers/0fd04df0-0f0f-4238-9e6a-13737d05ea76/badge.svg)](https://vouch.tools/servers/0fd04df0-0f0f-4238-9e6a-13737d05ea76)