mergesafe-mcp

MergeSafe's findings for your own coding agent (Claude Code, Cursor, or anything else that speaks MCP over stdio). Your agent reads what MergeSafe found on a pull request, fixes it on your machine, replies on the thread, and asks for a new review.

Install

uvx mergesafe-mcp                 # run without installing
uv tool install mergesafe-mcp     # or install it

From source: uv tool install git+https://github.com/mergesafe-ai/mergesafe-mcp

Configure

Claude Code

claude mcp add mergesafe --env MERGESAFE_API_KEY=ms_live_... -- mergesafe-mcp

Cursor (~/.cursor/mcp.json or .cursor/mcp.json)

{
  "mcpServers": {
    "mergesafe": {
      "command": "mergesafe-mcp",
      "env": { "MERGESAFE_API_KEY": "ms_live_..." }
    }
  }
}

Then ask your agent: "Fix MergeSafe's blocking findings on PR 42 in acme/widgets."

What leaves your machine

• To MergeSafe: your API key, the repo name and the PR number. MergeSafe's API returns the review's index (severity, title, file, line) and no code.
• To GitHub: your own token, to read comments you can already see on github.com and to post your replies.
• Your agent writes the fixes locally, with your tokens. MergeSafe never generates or applies a patch.