# MCP Selection Lab

- Registry name: `io.github.ChanghuLiu/mcp-selection-lab` · version 0.5.2
- Categories (automatic, keyword rules): Other
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.ChanghuLiu%2Fmcp-selection-lab
- Server page: https://mcpstation.net/s/io.github.ChanghuLiu--mcp-selection-lab.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://agenttrustlab.com/mcp`

## Tools (as reported by the server, not verified)

- `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
- `get\_selection\_report`: Read and agent-enrich an existing public scan report by id; no new target request or model call.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html