Skip to main content
Glama

mcp-audit

MCP server 安全审计 CLI。静态扫描一个 MCP server 的源码或 tool 定义,找出可被恶意 server 触发的危险模式。

为什么

Agent 会接入陌生的 MCP server,等于给对方一个能读文件、读环境变量、执行命令的入口。一个看似无害的 server,tool 定义里可能藏着 shell=True、eval、或读取你的 AWS 密钥。装之前先扫一遍,把风险看得见。

Related MCP server: mcp-audit

30 秒看效果

不用装、不用配,把仓库里的样例文件扫一遍(真实输出,2026-11-06 在 Python 3.14 上跑):

$ python3 mcp_audit.py tests/sample_vuln.py
[CRITICAL] tests/sample_vuln.py:10  shell 命令执行  (call:os.system)
[CRITICAL] tests/sample_vuln.py:12  subprocess shell=True(命令注入面)  (shell_injection)
[CRITICAL] tests/sample_vuln.py:14  动态代码执行  (call:eval)
[     LOW] tests/sample_vuln.py:4  导入 subprocess(仅在使用处才相关)  (import:subprocess)
[    HIGH] tests/sample_vuln.py:12  子进程调用(需确认 shell=True)  (call:subprocess.run)

你拿到的是「文件:行号 + 规则名 + 为什么危险」,可以直接贴进 issue 或 PR 评论。

扫什么

类别

规则示例

严重度

命令注入

os.system / os.popen / subprocess shell=True / eval / exec

CRITICAL

危险子进程

subprocess.run/Popen/call(未确认 shell)

HIGH

敏感信息泄露

os.environ.get("AWS_SECRET_ACCESS_KEY") 等

HIGH

危险反序列化

pickle / yaml.load

MEDIUM

危险 import

subprocess / child_process

HIGH/LOW

tool 描述投毒

描述里的隐藏指令("ignore previous instructions"、"do not tell the user")、夹带指令的不可见/双向控制字符、直接写在描述里的可执行片段

CRITICAL/HIGH/MEDIUM

用法

# 扫描单个文件
python3 mcp_audit.py path/to/server.py

# 扫描整个目录(递归 .py/.js/.ts/.json,跳过 node_modules/.git/venv)
python3 mcp_audit.py path/to/mcp-server/

# 默认跳过测试/样例/fixture 文件,避免测试噪音干扰报告;如需扫描测试文件:
python3 mcp_audit.py path/to/mcp-server/ --include-tests

# JSON 输出(接 CI/管道)
python3 mcp_audit.py path/to/server.py --json

输出按严重度降序:CRITICAL > HIGH > MEDIUM > LOW > INFO。

JSON 形式的 tool 清单(含 tools 数组)会额外跑一遍描述面检查,不需要源码即可用。描述面是启发式:always call 这类弱信号降为 MEDIUM,需人工确认上下文。

自测:python3 -m unittest discover -s tests -v(23 项,覆盖崩溃回归、跳过逻辑、描述面投毒的正负样本;装 mcp SDK 后 3 项 MCP 接口用例不再 skip)。

运行

依赖仅 Python 3.9+ 标准库,无需安装。

python3 mcp_audit.py tests/sample_vuln.py

局限

  • 静态分析,不执行代码,无法覆盖运行时动态构造的命令/路径。

  • 有误报(比如 subprocess.run 未开 shell 也会提示确认)和漏报(混淆过的代码)。

  • 它是第一道筛查,不是审计结论;CRITICAL/HIGH 项仍需人工确认上下文。

CI 接入(GitHub Actions)

# .github/workflows/mcp-audit.yml
name: mcp-audit
on: [push, pull_request]
jobs:
  scan:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.11' }
      - name: Scan for dangerous MCP patterns
        run: |
          # 本项目不做 pip 发布:把 mcp_audit.py 复制进你自己仓库(如 scripts/)再调用
          python3 scripts/mcp_audit.py . --json

每次 push/PR 自动跑,发现 CRITICAL 记入流水线日志。

付费

  • $49 自助报告:给一个公开仓库地址,24 小时内回带文件/行号的报告,不执行你的代码、不留源码。 下单与样例:https://web3project.top/mcp-audit

  • $99 固定范围服务:帮你接 CI、写逐条发现与复现说明。范围见 SCOPE.md。

自己本地跑永远免费,MIT。

降噪(2026-11-18)

拿真实公开仓库跑才发现,「正则命中就算漏洞」会让报告失去意义:modelcontextprotocol/servers 一次刷出 247 条发现、其中 124 条 CRITICAL,绝大多数来自 package-lock.json 里的包名和 // cp.exec(...) 这样的注释行。

改法:锁文件跳过;JSON 只做 tool 定义检查;JS/TS 先剥注释与字符串字面量;.exec( 这类方法调用 不再当作全局函数(另加 child_process 引入规则兜住真实用法);dangerous_fs、import:subprocess 降级;同一文件同类问题最多列 3 处。

结果:同一个仓库 247 → 155 条,CRITICAL 124 → 12 条;另测一个 107★ 的仓库 HIGH 从 145 降到 24。 回归测试在 tests/test_scan_noise.py。

状态

MVP。基于 AST(Python)+ 正则兜底(JS/TS/通用)。规则集后续可扩展(越权文件路径数据流、网络出站白名单等)。

Use as an MCP server

mcp-audit 也能作为一个 stdio MCP server 被 agent 直接调用(目录收录要求这一层)。扫描逻辑与 CLI 完全同一套(mcp_audit.scan_target),不是第二份实现。

安装

python3 -m venv .venv && . .venv/bin/activate
pip install -r requirements-mcp.txt   # 只有 mcp 一个运行时依赖
# 然后(可选)装到 PATH 或直接用绝对路径

配置

Claude Desktop(claude_desktop_config.json):

{
  "mcpServers": {
    "mcp-audit": {
      "command": "/absolute/path/to/.venv/bin/python",
      "args": ["/absolute/path/to/mcp_server.py"]
    }
  }
}

通用 mcpServers 写法(Cursor / Cline / Continue 等):

"mcpServers": {
  "mcp-audit": {
    "command": "python",
    "args": ["/absolute/path/to/mcp_server.py"]
  }
}

工具

scan_mcp_server:

参数

类型

必填

说明

path

string

是

要扫描的绝对路径(文件或目录)

include_tests

boolean

否(默认 false)

是否连测试/fixture 一起扫

返回单条 text content,内容是 JSON:

{
  "target": "/path/to/target",
  "finding_count": 8,
  "findings": [
    {"severity": "critical", "rule": "call:os.system", "file": ".../evil.py", "line": 10, "snippet": "shell 命令执行"}
  ],
  "scanned_files": 1
}

severity 取值:critical / high / medium / low / info(保留 CRITICAL 与 INFO 两级,不压成 high/low,否则 RCE 面会和提示级线索同档)。 路径不存在或不是绝对路径时返回结构化错误({"error": "path_not_found"}),不会抛栈。

实跑示例(本地真实 stdio 往返,节选)

先 initialize,再 notifications/initialized,然后 tools/list / tools/call:

→ {"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"evidence","version":"0"}}}
← {"jsonrpc":"2.0","id":1,"result":{"capabilities":{"prompts":{"listChanged":false},"resources":{"listChanged":false,"subscribe":false},"tools":{"listChanged":false}},"protocolVersion":"2025-06-18","serverInfo":{"name":"mcp-audit","version":""}}}

→ {"jsonrpc":"2.0","id":2,"method":"tools/list"}
← {"jsonrpc":"2.0","id":2,"result":{"tools":[{"name":"scan_mcp_server","description":"审计一个 MCP server 项目(本地路径)的安全风险,返回结构化风险清单","inputSchema":{"properties":{"path":{"title":"Path","type":"string"},"include_tests":{"default":false,"title":"Include Tests","type":"boolean"}},"required":["path"],"type":"object","title":"scan_mcp_serverArguments"}}]}}

→ {"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"scan_mcp_server","arguments":{"path":"/home/jam/projects/mcp-audit/tests/sample_vuln.py"}}}
← {"jsonrpc":"2.0","id":3,"result":{"content":[{"text":"{\n  \"target\": \"/home/jam/projects/mcp-audit/tests/sample_vuln.py\",\n  \"finding_count\": 8,\n  \"findings\": [\n    {\n      \"severity\": \"critical\",\n      \"rule\": \"call:os.system\",\n      \"file\": \"/home/jam/projects/mcp-audit/tests/sample_vuln.py\",\n      \"line\": 10,\n      \"snippet\": \"shell 命令执行\"\n    }, …后续 7 条略…\n  ]\n}","type":"text"}]}}

(outputSchema 与 title 等字段由 SDK 自动生成,上面为节选。)

Remote (streamable-http)

同一个 tool 也能以 streamable-http 挂到公网路径上(端点固定 /mcp),供只收远程服务的注册表收录:

python3 mcp_server.py --http --host 127.0.0.1 --port 8897
# 端点: http://127.0.0.1:8897/mcp  (默认 host 127.0.0.1 / port 8000)

不带参数时行为不变,仍是 stdio(run("stdio"),stdout 只走 JSON-RPC,不打印任何日志)。

仓库根的 server.json 是官方注册表(registry.modelcontextprotocol.io)的提交清单,字段与 server.schema.json 对齐;version 与 mcp_server.__version__ 由测试保证一致:

curl -s -X POST https://registry.modelcontextprotocol.io/v0/validate \
  -H 'Content-Type: application/json' -d @server.json
# {"valid":true,"issues":[]}

注:description 有 100 字符上限(超了返回 422 expected length <= 100)。

Available Tools

5 tools
explain_ruleB

查询单条规则的严重度、含义与修复建议

Inputs: rule (required).

list_rulesA

列出扫描器的全部规则(规则 id、严重度、说明、修复建议),用于判断这套扫描覆盖什么

Inputs: no named parameters.

scan_mcp_serverB

审计一个 MCP server 项目(本地路径)的安全风险,返回结构化风险清单

Inputs: path (required), include_tests.

scan_public_repoA

扫描公开仓库(github.com / gitlab.com / gitee.com)里的 MCP server 安全风险。只读克隆,扫描后立即删除。

Inputs: repo_url (required).

scan_to_sarifA

扫描本地路径或公开仓库并直接返回 SARIF 2.1.0 文档(可上传 GitHub code scanning)

Inputs: path, repo_url, include_tests.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 5 tools

    Disambiguation4/5

    The three scan tools have some overlap because scan_to_sarif accepts local paths and public repos, overlapping scan_mcp_server and scan_public_repo. However, their outputs and targets are described clearly enough that an agent can distinguish them: SARIF export versus structured risk lists versus public-repo scanning.

    Naming Consistency4/5

    All tool names use snake_case and begin with a verb: list_rules, explain_rule, scan_mcp_server, and scan_public_repo follow a clear verb_noun pattern. scan_to_sarif is a minor deviation because it names an output format rather than a target object, but it remains predictable.

    Tool Count5/5

    Five tools are well scoped for a focused MCP security-audit server: rule discovery, rule explanation, local scanning, public-repo scanning, and SARIF export. Each tool has a clear role and the set does not feel padded.

    Completeness4/5

    The set covers the core workflow: inspect rules, explain a rule, scan local MCP servers, scan public repos, and export SARIF. Minor gaps remain, such as no rule filtering/configuration, no batch or history view, and no result comparison, but the main audit lifecycle is present.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Audits MCP server configurations for security risks including capability inventory, SSRF, prompt injection, and drift detection. Works in read-only mode and can also be used as an MCP server to let AI agents audit their own attack surface.
      182 PyPI
      4
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Audits MCP server configurations and packages for security risks such as typosquats, credential exposure, and malicious code, with zero dependencies and no execution.
      1
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Scans MCP client configurations for risky settings without starting the configured servers. Returns redacted findings through a read-only MCP server and CLI
      2
      26 PyPI
      MIT