MCPVetter

com.mcpvetter由 mcpvetter.com 发布官方发布者v0.1.3更新于 Nov 7, 2026

审计你的 MCP 服务器是否存在被投毒的工具和泄露的密钥，并检查 AI 生成的代码是否有缺陷。

AI 翻译由 AI 模型根据下方的原文描述翻译，可能有误。

原文描述

Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.

已验证Streamable HTTP可网页运行

概览

MCPVetter 的托管 MCP 服务（mcpvetter.com），由 mcpvetter.com 发布；需要 OAuth 登录；Streamable HTTP；7 个工具。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

发布者
mcpvetter.com
端点
mcpvetter.com
文档
mcpvetter.com
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 MCPVetter，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.mcpvetter%2Fmcpvetter/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "mcpvetter": {
      "type": "http",
      "url": "https://mcpvetter.com/mcp"
    }
  }
}

README

mcpvetter

Audit the MCP servers your AI assistant uses: leaked secrets, unpinned or look-alike packages, risky launch commands, unencrypted remote servers, over-broad file access, poisoned tool descriptions, hidden Unicode, tool shadowing, and silent tool changes.

bash
npx mcpvetter scan          # discover + static scan, offlinenpx mcpvetter scan --live   # also read each server's tool descriptions (asks first)

Local, no account, no telemetry. A static scan reads your MCP config files and nothing else. It never changes a config file.

What a finding looks like

■ github[HIGH] Plain-text secret in MCP config  MCP-SECRET-001 · confidence high · static    server: github  file: .mcp.json    Evidence: env GITHUB_PERSONAL_ACCESS_TOKEN=ghp_…[redacted 40 chars] (GitHub token)    Why it matters: Anything that can read this file, including other tools, backups, sync    folders, and anyone the file is shared or committed with, gets a working credential.    Fix: Rotate the credential first (removing it does not un-leak it), then reference it    from the environment or a secret store instead of the literal value. Claude Code and    Claude Desktop expand "${VAR}" in .mcp.json, Cursor expands "${env:VAR}", and VS Code    supports "${input:...}" prompts or an "envFile".

Every finding has a stable ID, separate severity and confidence, redacted evidence, a plain-English reason, and a concrete fix. What each rule checks, and how, is published at mcpvetter.com/rules and in src/scanner/rules.

Clients discovered

Claude Code (~/.claude.json, .mcp.json), Claude Desktop, Cursor (~/.cursor/mcp.json, .cursor/mcp.json), VS Code (mcp.json, settings.json, .vscode/mcp.json), Windsurf, Gemini CLI. Or pass --config <file>.

Commands

mcpvetter scan [--live] [--yes] [--config <file>]... [--json [file]] [--summary] [--fail-on <severity>]mcpvetter list                               inventory onlymcpvetter explain MCP-POISON-001             explain a findingmcpvetter rules                              every rule and what it checksmcpvetter suppress <ID> --server <name> --reason "<why>"mcpvetter accept <server> --reason "<why>"   accept a server's new tool fingerprintmcpvetter serve                              run as a local MCP server (stdio)

Exit codes: 0 no findings at or above --fail-on (default high), 1 findings at or above it, 2 scan could not complete. Use it in CI as-is.

Suppressions are always listed in the report, so a shared report cannot hide them.

About --live

To read tool descriptions, MCPVetter has to start each stdio server, exactly as your AI client does every time it launches. It asks before each one, runs it with a minimal environment plus the env your config declares, and only calls initialize, tools/list, prompts/list, and resources/list. It never calls a tool. The first approved probe records a fingerprint of each server's tools in ~/.mcpvetter/fingerprints.json; later probes report any change (a "rug pull") with a before/after diff.

Inside your AI assistant

Claude Code:

bash
claude mcp add mcpvetter -- npx -y [email protected] serve

Cursor / VS Code / Claude Desktop (mcpServers or servers):

json
{ "mcpServers": { "mcpvetter": { "command": "npx", "args": ["-y", "[email protected]", "serve"] } } }

Then ask: "audit my MCP setup".

Free without an account: check_mcp_setup, explain_finding. With an API key (MCPVETTER_API_KEY, free tier available at mcpvetter.com/account): review_code, secure_pattern, start_lab, check_lab, team_posture. Code review runs on your machine; only rule IDs and counts are sent for your history. Plans: mcpvetter.com/pricing.

Privacy

  • Static analysis runs on your machine. Without an API key, MCPVetter makes no network requests.
  • With an API key, only rule IDs, severities, and counts are sent. Never code, evidence, file paths, or server names.
  • Reports redact secret values by default.

License

MIT

来源：README.md，提交 cffd157

工具

7

review_code

Review code for security flaws

Check a code snippet for security flaws before presenting or committing it. Call this before showing the user any generated code that handles authentication, sessions, database queries, user or LLM input, HTML rendering, file uploads, outbound URL fetches, secrets, or MCP configuration. Returns prioritised findings, each with evidence, a concrete fix, and a 5-minute lab. Analysis is static and deterministic; it checks at the moment of generation and is not a guarantee.

输入参数code必填filenamelanguageai_generated

explain_finding

Explain a security finding

Explain an MCPVetter finding in plain English: why it matters, how the flaw is triggered (in general, defensive terms), why a code reviewer would block it, and how to fix it. Call this when the user asks what a finding ID (like CODE-SQLI-001 or MCP-POISON-001) means or why it matters.

输入参数id必填

secure_pattern

Get the secure version of a coding pattern

Return a vetted secure code example for a pattern in the user's stack, the insecure version to avoid, and a reviewer checklist. Call this when writing code for: database queries, secrets/API keys, login and sessions, rendering user content as HTML, sending user input to an LLM, using LLM output, file uploads, fetching URLs/webhooks, or configuring MCP servers. Example requests: "parameterised query in Node", "safe handling of LLM output in Python".

输入参数stackrequest必填

start_lab

Start a 5-minute secure-coding lab

Start a short hands-on lab that fixes one vulnerability in realistic AI-generated code. Call this when the user wants to learn how to fix a finding, or after review_code reports a finding with a lab. Pass a lab id (lab-02-sqli) or a finding id (CODE-SQLI-001). Then help the user fix the snippet and submit it with check_lab.

输入参数lab_idfinding_id

check_lab

Check a lab solution

Verify a fixed snippet for a lab started with start_lab. Runs the lab's security checks on the code and records progress. Call this when the user says their lab fix is ready.

输入参数code必填lab_id必填

check_mcp_setup

Audit MCP server setup

Audit the MCP servers configured on this machine (Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI) for leaked secrets, unpinned or look-alike packages, risky launch commands, unencrypted remote servers, over-broad file access, and dangerous server combinations. Call this when the user asks whether their MCP setup or a server is safe. Static and local; for tool-description poisoning run `npx mcpvetter scan --live` in a terminal.

输入参数config

team_posture

Team security posture

Team plan: aggregated, de-identified counts of recurring code findings, MCP risk by category, and lab completion for the user's team over the last 30 days. No code or per-developer detail. Call this when a team lead asks how exposed the team is or which flaws keep recurring.

无需输入参数。

版本历史

1
  1. v0.1.3最新Nov 3, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分