io.github.ChanghuLiu/mcp-selection-lab

MCP Selection Lab

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

0.5.1
Version
remote
Transport
3
Tools

Security review

Review passed

Reviewed 23h ago.

  • tools: 3 tools scanned
  • metadata: scanned

No findings.

Tools (3)

  • selection_lab_info

    Get free service capabilities, limits, privacy and connection details; does not scan a target.

  • 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.

  • get_selection_report

    Read and agent-enrich an existing public scan report by id; no new target request or model call.