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.
We read the source, 8 h ago · rules 995398eba69f
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.
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.
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.
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.
claude mcp add benchwarmers -- npx -y @wendellresearch-ai/benchwarmers
{
"mcpServers": {
"benchwarmers": {
"command": "npx",
"args": [
"-y",
"@wendellresearch-ai/benchwarmers"
]
}
}
}
[mcp_servers.benchwarmers]
command = "npx"
args = ["-y", "@wendellresearch-ai/benchwarmers"]
{
"mcpServers": {
"benchwarmers": {
"command": "npx",
"args": [
"-y",
"@wendellresearch-ai/benchwarmers"
]
}
}
}
{
"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)).
Collects the open points of your AI conversations on a color board, so no idea or decision is lost.
Anki addon that exposes your flashcard collection to AI assistants via a local MCP server.
Goal-oriented conversations and next-question selection through the Zelinqa API.
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
Connect AI clients to your Dactic work context through a hosted MCP service.
Your agent asks before it acts, so the same real-world action is attempted at most once.
The official Upwork MCP server, letting AI agents connect to Upwork and act on your behalf.
Use Chinese LLMs through the SinoGate OpenAI-compatible API.
Answers built from our own checks of this server.