safe-fix-mcp
Enables scanning Python repos for dead code and automatically drafting a branch + PR for the safe subset (unused single-name imports) after running the repo's full test suite. All other findings are reported without modification, and a human always merges.
README
safe-fix-mcp
<!-- mcp-name: io.github.pamela-0/safe-fix-mcp -->
A real MCP server that finds dead code in a Python repository and proposes a branch + PR for the one class of finding that's actually safe to auto-remove: unused imports on a single-name import line. Everything else it finds — unused functions, classes, unused dependencies — stays report-only. A human always merges. This tool never merges anything itself.
Why this exists
Most "dead code" tools stop at reporting. The ones that go further usually delete with no safety net. This does neither: it drafts a real, minimal, reviewable PR, gated on the target repo's own full test suite actually passing after the removal — not a heuristic, a real pytest run. If the suite fails, nothing is committed or pushed; the repo is left exactly as it started.
Tools
scan_dead_code(repo_path=".", min_confidence=60)
Read-only. Runs vulture (dead code) and deptry (dependency issues) and returns a human-readable list of findings. Never modifies anything.
propose_removal_pr(repo_path=".")
- Refuses on a dirty working tree — never edits on top of uncommitted work.
- Filters to unused imports at ≥90% vulture confidence, on single-name import lines only (
from x import y, zis skipped — removing the whole line would silently removeztoo). - Creates a real branch, removes the qualifying imports, runs the repo's real full test suite.
- Only on a real pass: commits, pushes, and tries to open a PR via
gh pr create. - If
ghisn't installed/authenticated, the branch is still committed and pushed for real — only PR creation degrades, with the real error returned so you can open it manually.
Install
pip install safe-fix-mcp
Add to your MCP client config (e.g. Claude Code):
claude mcp add safe-fix-mcp -- safe-fix-mcp
Or run directly for local testing:
python -m safe_fix_mcp.server
Installing from source instead of PyPI:
pip install -e .
Requirements
- Python ≥ 3.10
giton PATHgh(GitHub CLI) on PATH and authenticated, if you wantpropose_removal_prto actually open the PR — without it, the branch still gets pushed for real, and the tool tells you to open the PR by hand.
Development
pip install -e ".[dev]"
pytest
Known limitation
vulture flags scan_dead_code/propose_removal_pr themselves as "unused" — a known false-positive class, not a real bug: they're dispatched by the @mcp.tool() decorator at runtime, not called directly anywhere in the source, so static call-graph analysis can't see the real caller (the MCP framework itself).
Verifying it for real
scripts/verify_real_client.py launches the packaged server as a real subprocess and talks to it with the real mcp.client.ClientSession — the same path a real MCP client uses. Useful as a smoke test after any change:
python scripts/verify_real_client.py
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。