mcp-code-review

MCP Code Review Server

Professional-grade code review for your AI coding assistant. Runs entirely locally — no SaaS fees, no code uploads.

Install

The server is available as aicraft-code-review on PyPI and connects via stdio:

{
  "mcpServers": {
    "mcp-code-review": {
      "command": "uvx",
      "args": ["--from", "aicraft-code-review", "--with", "mcp<2", "mcp-code-review"]
    }
  }
}

Or install with pip/uv:

pip install aicraft-code-review
# or
uv tool install aicraft-code-review

Then add the server to your MCP client (Claude Code, Cursor, Cline, etc.).

Review workflow

1. Run review_code against a git range (e.g. HEAD~3..HEAD) or two branches.
2. Filter findings by author with --author to focus on your own changes.
3. Open the generated HTML report — findings include severity ratings, file locations, and actionable fixes.

What it checks

• Deterministic local security-pattern checks (injection, deserialization, credentials, and XSS patterns)
• Bug and vulnerability detection
• N+1 query analysis
• Performance profiling (hotspots, I/O, memory)
• Style and complexity issues (configurable rules)

Tips

• Review small diffs frequently; the report is easiest to consume per-PR.
• Treat severity ratings as a queue: Critical/High first, then Medium/Low.
• The report is fully local — safe for proprietary code.