A standardized testing harness for MCP servers and agent workflows
npx -y mcp-eval-runner{
"YOUR_API_KEY": "YOUR_SECRET_VALUE"
}Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
{
"mcpServers": {
"io-github-dbsectrainer-mcp-eval-runner": {
"command": "npx",
"args": [
"-y",
"mcp-eval-runner"
],
"env": {
"YOUR_API_KEY": "YOUR_SECRET_VALUE"
}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonNo remote HTTP endpoint is advertised. Use the package or stdio setup shown in Install.
mcp-eval-runner is an MCP server for A standardized testing harness for MCP servers and agent workflows. It supports STDIO transport.
Use the generated config in Install. This server runs with npx -y mcp-eval-runner; add any required environment variables before starting your client.
Choose the Claude Desktop tab in Install and copy the config for npx -y mcp-eval-runner. Add required environment variables before starting Claude Desktop.
Choose the Claude Code tab in Install and copy the config for npx -y mcp-eval-runner. Add required environment variables before starting Claude Code.
Choose the Codex tab in Install and copy the config for npx -y mcp-eval-runner. Add required environment variables before starting Codex.
Choose the Cursor or VS Code tab in Install and copy the config for npx -y mcp-eval-runner. Add required environment variables before starting Cursor or VS Code.
mcp-eval-runner uses STDIO transport. Use the package or command config in Install.
mcp-eval-runner inventory is listed when the MCP endpoint exposes tools, resources, or prompts. Some servers require auth first.
mcp-eval-runner is marked with Auth required by registry metadata auth. You may need provider login, an API key, a bearer token, or a session header.
| Package | Registry | Version | Inputs |
|---|---|---|---|
mcp-eval-runnerstdio | npm | 1.0.0 | Env: YOUR_API_KEY required secret |