Benchwarmers MCP Server: Install & Setup

Install Benchwarmers in Claude Code

npm

Claude Code

claude mcp add benchwarmers -- npx -y @wendellresearch-ai/benchwarmers

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "benchwarmers": {
      "command": "npx",
      "args": [
        "-y",
        "@wendellresearch-ai/benchwarmers"
      ]
    }
  }
}

PyPI (uv)

Claude Code

claude mcp add benchwarmers -- uvx benchwarmers

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "benchwarmers": {
      "command": "uvx",
      "args": [
        "benchwarmers"
      ]
    }
  }
}

Frequently asked questions

What does the Benchwarmers MCP server do?

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

Is the Benchwarmers MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Benchwarmers run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Benchwarmers to Claude Code?

Run: claude mcp add benchwarmers -- npx -y @wendellresearch-ai/benchwarmers

More ai agents & coding agents MCP servers

View all

Better Design

14.5k

better-designs/better-design-plugin

A design harness for AI coding agents: design systems, design principles, icons and UI review.

Local + RemoteAccount needed

BackBond Agent Scan

BackBond/agent-scan

Vet MCP tool manifests before attachment; returns block, review, or no blocking finding.

LocalFree

Boot Doctor

pamela-0/boot-doctor-mcp

Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.

LocalFree

Awaitless

xpluspro/Awaitless

Durable execution and named concurrency queues for coding agents across local, SSH, and Slurm.

LocalFree

Brevet

BrightbeamAI/brevet

Change control for what AI agents learn: humans promote, releases are signed, rules can be recalled

LocalFree

Audit

archonics/mcp-audit

Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.

LocalAccount needed