Installation

pip install mcpbr && mcpbr init && mcpbr run -c mcpbr.yaml -n 1 -v

That's it. For the full setup guide, read on.

Prerequisites

API Key

export ANTHROPIC_API_KEY="sk-ant-..."

Sign up at console.anthropic.com to get your API key.

Claude Code CLI

npm install -g @anthropic-ai/claude-code

Docker

docker info

Ensure Docker is installed and running.

Installation Methods

From PyPI (Recommended)

pip install mcpbr

From npm

# Run with npx (no installation)
npx mcpbr-cli run -c config.yaml

# Or install globally
npm install -g mcpbr-cli
mcpbr run -c config.yaml

From Source

git clone https://github.com/supermodeltools/mcpbr.git
cd mcpbr
pip install -e .

With uv

uv pip install mcpbr

Verify Installation

# Check mcpbr is installed
mcpbr --version

# List supported models
mcpbr models

# Generate a test config
mcpbr init -o test-config.yaml

Supported Models

Run mcpbr models to see the full list.

Apple Silicon Notes

On ARM64 Macs (M1/M2/M3/M4), x86_64 Docker images run via emulation. This is automatic and requires no configuration. If you experience issues:

softwareupdate --install-rosetta

Next Steps

• Configuration — Configure your MCP server
• CLI Reference — Explore all commands
• Benchmarks — Browse available benchmarks
• Examples — Browse 25+ example configurations

Sitemap · llms.txt · evaldriven · SchemaFlux

Created by Grey Newell