mcpbeat Sign in

MCP Eval Runner MCP Server

local only

MCP Eval Runner runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 23 Sep 2026.

A standardized testing harness for MCP servers and agent workflows

Installs per day peak 12 · avg 4 · -37% w/w
a month agotoday
35
Installs / week
npm · mcp-eval-runner
0
Stars
0 open issues
23 Sep 2026
Last commit
no releases in 90 days
MIT
License
TypeScript

What the code does

We read the source, 5 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable src/fixture-library.ts:89
    const destPath = path.join(dest, fileName);
Runs an external command src/runner.ts:124
    this.proc = spawn(command, args, {

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add mcp-eval-runner -e 'YOUR_API_KEY=<YOUR_API_KEY>' -- npx -y mcp-eval-runner
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp-eval-runner": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-eval-runner"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp-eval-runner]
command = "npx"
args = ["-y", "mcp-eval-runner"]
env = { YOUR_API_KEY = "<YOUR_API_KEY>" }
.cursor/mcp.json
{
  "mcpServers": {
    "mcp-eval-runner": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-eval-runner"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mcp-eval-runner": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-eval-runner"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Put your own value in place of <YOUR_API_KEY> (Your API key for the service). The author’s registry entry marks it as required.

Alternatives to MCP Eval Runner

same job, measured the same way
AndroidMCP Framework
by kshivam1177

MCP server and CLI for Android development and change-aware Android and Flutter testing workflows.

9 072 installs/wk local only
Testkube MCP
by kubeshop

MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants

answering
E
Elias MCP Sample Server
by elpadev

A sample MCP server for testing

113 installs/wk local only
Testers.ai CARBON Test Harness Lite
by jarbon

Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.

local only
U
Ubitoushiha My First MCP
by obitouchiha930

My first MCP server for testing

48 installs/wk local only
pagent
by aihumin

A/B testing MCP server for pagent: create, run and review A/B tests on your live website.

answering
C
CTnP MCP Server
by jitsmaster

Ingeniux CTnP MCP server for personalization, A/B testing, and audience management.

local only
Testdino MCP
by testdino-inc

A MCP server for TestDino

1 202 installs/wk local only

MCP Eval Runner — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Eval Runner?
MCP Eval Runner runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package mcp-eval-runner was installed 35 times last week.
How do I connect MCP Eval Runner?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls mcp-eval-runner straight from npm; nothing to host, nothing to sign up for.
How many people use MCP Eval Runner?
The npm package mcp-eval-runner was installed 35 times in the last week. Week over week that is -37%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is MCP Eval Runner open source?
Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.