MCP Selection Lab

io.github.ChanghuLiu/mcp-selection-lab · v0.5.2

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Can write (some tools are not declared read-only)
Capabilities declared	experimental, prompts, resources, tools
Tool definitions	3 tools · with description 100% · input schema is an object 100% · read/destructive hints 100%

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

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

claude mcp add --transport http mcp-selection-lab https://agenttrustlab.com/mcp

{
  "mcpServers": {
    "mcp-selection-lab": {
      "url": "https://agenttrustlab.com/mcp"
    }
  }
}

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.

Repository · Website · JSON · Text for agents · Registry updated 2026-10-13