概要

Benchmark your MCP server against real GitHub issues. One command, hard numbers. Stop guessing if your MCP server actually helps. Get hard numbers comparing tool-assisted vs. baseline agent performance on real GitHub issues. If this is useful, please star our tools — it helps us grow: Real metrics showing whether your MCP server improves agent performance on SWE-bench tasks. No vibes, just data. MCP servers promise to make LLMs better at coding tasks. But how do you prove it? mcpbr runs controlled experiments: same model, same tasks, same environment - the only variable is your MCP server. You get: - against a baseline agent - from SWE-bench (not toy examples) - via Docker containers with pinned dependencies - SWE-bench Verified Is Broken: 5 Things I Found in the Source Code - SWE-bench Tests Run 6x Faster on ARM64 with Native Containers

README

以下は原文 README の抜粋です。原文を見る。

# One-liner install (installs + runs quick test)
curl -sSL https://raw.githubusercontent.com/greynewell/mcpbr/main/install.sh | bash

# Or install and run manually
pip install mcpbr && mcpbr run -n 1

インストール