Developer Infrastructure · Product Profile v2

MCP Selection Lab

A benchmark and scan toolkit for investigating how agents choose among MCP tools.

Evidence Tested Verified 2026-09-12

What is it?

A benchmark and scan toolkit for investigating how agents choose among MCP tools.

Included because: Existing measurement infrastructure that supplies canonical Agent Trust Lab evidence.

Provider / organizationChanghu Liu
Homepage / projecthttps://mcp-selection-lab-production.up.railway.app/
Repositoryhttps://github.com/ChanghuLiu/mcp-selection-lab
MCP endpointhttps://mcp-selection-lab-production.up.railway.app/mcp
AuthenticationNONE for documented public discovery tools
Transportstreamable-http
Tool count3
Last verified2026-09-12

What evidence do we have?

Evidence state: EVIDENCE_TESTED

Existing S2 selection evidence and Reliability Explorer records remain canonical; this profile does not rescore them.

Evidence links point to existing canonical records; this page does not duplicate or re-score measurement data.

What can an agent use it for?

  • Run bounded metadata-only selection-readiness scans.
  • Read existing selection evidence and reports.

What type of tool surface does it expose?

Three public discovery/report tools; no target business-tool execution.

What remains untested or unknown?

  • Current behavior may differ from the cited source snapshot or documentation.

Source provenance

Identity verification: VERIFIED; checked 2026-09-12. No claim is submitted on behalf of the project.

Has Agent Trust Lab tested it?

Yes — existing evidence is linked above.

Request an independent evaluation — US$249 →