repo-guardian
repo-guardian
MCP 服务器,用于提供仓库健康工具,让任何智能体都能守护仓库——检测固定/未固定的依赖、许可证合规问题、硬编码的机密信息以及死代码。
功能特性
audit_dependencies — 解析
pyproject.toml、requirements*.txt和setup.py,识别可能遗漏安全补丁的固定版本,以及没有版本约束的依赖。check_licenses — 扫描已声明依赖的许可证合规问题(GPL/AGPL copyleft、未知许可证、与项目许可证不兼容的许可证)。
scan_for_secrets — 搜索 AWS 密钥、GitHub 令牌、Slack 令牌、Google API 密钥、Stripe 密钥、私钥块、密码赋值、bearer 令牌以及高熵字符串。
find_dead_code — 检测未使用的 Python 导入、未使用的函数以及孤立文件。
所有扫描器均为零依赖(仅使用标准库),并且绝不会让 MCP 会话崩溃——错误会作为工具结果返回。
Related MCP server: Celmis MCP Server
安装
pip install repo-guardian用于开发:
git clone https://github.com/prem-the-dev/repo-guardian.git
cd repo-guardian
pip install -e ".[dev]"快速开始 (Claude Desktop / Cursor / Windsurf)
添加到你的 MCP 客户端配置:
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"repo-guardian": {
"command": "python",
"args": ["-m", "repo_guardian"]
}
}
}Cursor (.cursor/mcp.json)
{
"mcpServers": {
"repo-guardian": {
"command": "python",
"args": ["-m", "repo_guardian"]
}
}
}Windsurf (.codeium/windsurf/mcp.json)
与上方 Cursor 的配置相同。
Gemini CLI (gemini/.gemini/.mcp.json)
{
"mcpServers": {
"repo-guardian": {
"command": "python",
"args": ["-m", "repo_guardian"]
}
}
}Hermes Agent
将附带的 mcp.json 复制到你的 Hermes 配置目录中,或与现有的 MCP 服务器配置合并:
cp mcp.json ~/.hermes/profiles/mcp-specialist/mcp.json
hermes profile reload{
"mcpServers": {
"repo-guardian": {
"command": "python",
"args": ["-m", "repo_guardian"]
}
}
}使用示例
配置完成后,任何智能体都可以调用这些工具:
审计依赖
audit_dependencies(path="/path/to/my-project")返回:
{
"status": "ok",
"scanned_files": ["pyproject.toml", "requirements.txt"],
"total_dependencies": 4,
"pinned_dependencies": [
{"name": "Django", "version_spec": "==4.2.7", "classification": "pinned"}
],
"potential_issues": [
{"type": "pinned_exact", "dependency": "Django", "message": "..."}
]
}检查许可证
check_licenses(path="/path/to/my-project")返回:
{
"status": "ok",
"project_license": "MIT",
"restricted_licenses": [],
"unknown_licenses": [...],
"potential_issues": []
}扫描机密
scan_for_secrets(path="/path/to/my-project", max_file_size_mb=5)返回:
{
"status": "ok",
"total_findings": 3,
"findings": [
{"type": "aws_access_key", "file": ".env", "line": 2, "confidence": "high"},
{"type": "github_token", "file": "config.py", "line": 5, "confidence": "high"}
]
}查找死代码
find_dead_code(path="/path/to/my-project")返回:
{
"status": "ok",
"unused_imports": [
{"type": "unused_import", "file": "main.py", "line": 3, "name": "unused_module"}
],
"unused_functions": [
{"type": "unused_function", "file": "main.py", "line": 12, "name": "unused_function"}
],
"orphaned_files": [...]
}运行测试
python -m pytest tests/ -v架构
graph TD
A[MCP Client<br/>Claude/Cursor/Windsurf/Hermes] -->|stdio JSON-RPC| B[MCP Server<br/>repo_guardian]
B --> C[Tool Registry<br/>tools/list + tools/call]
C --> D[audit_dependencies]
C --> E[check_licenses]
C --> F[scan_for_secrets]
C --> G[find_dead_code]
D --> D1[pyproject.toml parser]
D --> D2[requirements.txt parser]
D --> D3[setup.py parser]
E --> E1[SPDX license DB<br/>offline lookup]
E --> E2[Project license<br/>detect]
F --> F1[Pattern matchers<br/>AWS/GH/Slack/etc]
F --> F2[Shannon entropy<br/>high-entropy scan]
G --> G1[AST parser<br/>imports + defs]
G --> G2[Cross-file<br/>usage tracker]许可证
MIT
Available Tools
4 toolsaudit_dependenciesA
Audit Python project dependencies for outdated, missing or pinned-to-fixed-version packages. Reads pyproject.toml, requirements*.txt and setup.py/setup.cfg.
Inputs: path.
check_licensesA
Scan declared dependency licenses for potential compliance issues (e.g. GPL, AGPL, or missing license metadata).
Inputs: path.
find_dead_codeA
Detect unused Python imports, unused functions and orphaned files (e.g. files never imported or referenced).
Inputs: path.
scan_for_secretsB
Search the repository for hardcoded secrets, high-entropy tokens and other potential credential leaks.
Inputs: path, max_file_size_mb.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a clearly distinct concern: dependency hygiene, license compliance, secrets, and dead code. There is no meaningful overlap between them, so an agent can confidently select the right tool for a given task.
All four tool names follow the same imperative verb_noun pattern: audit_dependencies, check_licenses, scan_for_secrets, find_dead_code. The naming is uniform, predictable, and easy to extend with additional checks.
Four tools is a focused, well-scoped set for a repository auditing/guardian server. Each tool covers a meaningful area without redundancy or bloat.
The set covers the main repository health/security concerns: dependencies, licenses, secrets, and dead code. Minor gaps exist, such as no vulnerability/CVE scanning or remediation/generation tools, but the core read-only auditing surface is coherent and usable.
Related MCP Connectors
Security tools for coding agents: dependency advisory audits and evidence for remediation.
Remote MCP for tool license checks, vendor policy review, alternatives, and license receipts.
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
Free MCP security tools for AI coding agents. Check npm/PyPI package versions, identify known OSV vulnerabilities, compare with the latest releases, and review up to 3 dependencies before deployment.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables MCP-compatible AI agents to scan code for leaked secrets, copyleft licenses, unprotected routes, missing privacy policies, and risky card handling before committing or shipping.63 npmMIT

Celmis MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables querying indexed code across multiple repositories with file-level citations, reviewing pull requests, auditing dependencies, and exporting SBOMs and evidence packs through MCP tools.3AGPL 3.0- AlicenseBqualityBmaintenanceEnables auditing codebases for production readiness, including linting, testing, CI/CD, security, branch conventions, architecture, and an A–F quality scorecard via MCP tools.1510 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to scan codebases, persist and prioritize security findings against SLAs, retrieve CVE details, propose fixes, and create tickets through its tools. It also supports agent-assisted remediation drafting while enforcing human approval and preventing auto-merge.1MIT