mcpbeat Sign in

Benchwarmers MCP Server

by wendellresearch-ai Your server? Claim it
local only

Benchwarmers runs on your own machine — the client starts it, so there is no endpoint to ping. 2 874 installs a week from pypi. Last commit 8 Nov 2026.

Ask a collection of LLMs at once through your Benchwarmers server; verdicts pick the next panel.

Installs per day peak 887 · avg 112 · -15% w/w
a month agotoday
2 874
Installs / week
npm · @wendellresearch-ai/benchwarmers
1
Stars
0 open issues
8 Nov 2026
Last commit
11 releases in 90 days
MIT
License
Python

What the code does

We read the source, 8 h 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.

Runs an external command bin/benchwarmers.js:19
    const r = spawnSync(cmd, pre.concat(['-c', 'import sys; print("%d %d" % sys.version_info[:2])']), { encoding: 'utf8' });
        done = subprocess.run([bench_python(), *args], cwd=ROOT, capture_output=True, text=True,

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 benchwarmers -- npx -y @wendellresearch-ai/benchwarmers
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "benchwarmers": {
      "command": "npx",
      "args": [
        "-y",
        "@wendellresearch-ai/benchwarmers"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.benchwarmers]
command = "npx"
args = ["-y", "@wendellresearch-ai/benchwarmers"]
.cursor/mcp.json
{
  "mcpServers": {
    "benchwarmers": {
      "command": "npx",
      "args": [
        "-y",
        "@wendellresearch-ai/benchwarmers"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "benchwarmers": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@wendellresearch-ai/benchwarmers"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: BENCHWARMERS_URL (Your Benchwarmers server (default http://127.0.0.1:8122). Needs Python 3.11 or later on PATH), BENCHWARMERS_KEY (A gateway key, needed beyond this machine or where the server requires keys), BENCHWARMERS_TIMEOUT (Seconds to wait for a panel (default 900)).

Alternatives to Benchwarmers

same job, measured the same way
Kilt
by kiltwork

Collects the open points of your AI conversations on a color board, so no idea or decision is lost.

answering
AnkiMCP Server
by ankimcp

Anki addon that exposes your flashcard collection to AI assistants via a local MCP server.

local only
Zelinqa MCP
by zelinqa

Goal-oriented conversations and next-question selection through the Zelinqa API.

102 installs/wk local only
OpenMark
by openmark

Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.

10 tools answering
Dactic
by dactic

Connect AI clients to your Dactic work context through a hosted MCP service.

34 tools answering
Ratchet
by ratchetgate

Your agent asks before it acts, so the same real-world action is attempted at most once.

49 installs/wk 15 tools answering
U
Upwork MCP
by upwork-mcp

The official Upwork MCP server, letting AI agents connect to Upwork and act on your behalf.

answering
S
SinoGate MCP Server
by sinogate

Use Chinese LLMs through the SinoGate OpenAI-compatible API.

96 installs/wk local only

Benchwarmers — questions

Answers built from our own checks of this server.

Why is there no uptime for Benchwarmers?
Benchwarmers 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 @wendellresearch-ai/benchwarmers was installed 2 874 times last week.
How do I connect Benchwarmers?
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 @wendellresearch-ai/benchwarmers straight from npm; nothing to host, nothing to sign up for.
How many people use Benchwarmers?
The npm package @wendellresearch-ai/benchwarmers was installed 2 874 times in the last week. Week over week that is -15%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Benchwarmers open source?
Yes — it is published under the MIT licence, written in Python and 1 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.