mcp-eval-runner

About mcp-eval-runner

Use mcp-eval-runner with your agent

claude mcp add mcp-eval-runner -- npx -y mcp-eval-runner

{
  "mcpServers": {
    "mcp-eval-runner": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-eval-runner"
      ]
    }
  }
}

Frequently asked questions

What is mcp-eval-runner?

mcp-eval-runner is an MCP (Model Context Protocol) server by dbsectrainer in the App Automation category. A standardized testing harness for MCP servers and agent workflows

How do I connect mcp-eval-runner to Claude, Cursor, or another MCP client?

Install mcp-eval-runner from its npm package (mcp-eval-runner) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is mcp-eval-runner open source?

Yes — the source code is public at github.com/dbsectrainer/mcp-eval-runner.

Can AI agents pay to use mcp-eval-runner?

Not yet through Loomal — mcp-eval-runner is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.