Skip to content
mcp/skillhub

Eval Runner MCP Server

by dbsectrainerio.github.dbsectrainer/mcp-eval-runnerv1.0.0

A standardized testing harness for MCP servers and agent workflows

0Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active17d ago

Install Eval Runner MCP server

Install in Claude Code

claude mcp add eval-runner -e YOUR_API_KEY='<your-api-key>' -- npx -y mcp-eval-runner

Configuration

VariableRequiredSecretDescription
YOUR_API_KEYyesyesYour API key for the service

Freshness

Active — last maintenance signal 17d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-09-22 · 17d ago · GitHub

  2. Latest release

    2026-03-23 · 7mo ago · GitHub · v1.0.0

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-03-23 · 7mo ago · official registry · v1.0.0

FAQ

›How do I install the Eval Runner MCP server in Claude Code?

Run: claude mcp add eval-runner -e YOUR_API_KEY='<your-api-key>' -- npx -y mcp-eval-runner. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Eval Runner require an API key?

Yes. It expects YOUR_API_KEY, of which 1 is a secret.

›Can I use Eval Runner as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Eval Runner in the official MCP registry?

Yes, as io.github.dbsectrainer/mcp-eval-runner.

Alternatives to Eval Runner

Other testing & qa MCP servers.

View all