GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Local OpenAPI contract and breaking-change checks for AI agents.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"api-guardian": {
"command": "npx",
"args": [
"-y",
"mcp-api-guardian"
]
}
}
}在终端中运行这条命令
claude mcp add api-guardian -- npx -y mcp-api-guardian粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"api-guardian": {
"command": "npx",
"args": [
"-y",
"mcp-api-guardian"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"api-guardian": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-api-guardian"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 petrovicistefan 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.2)于19天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:GitHub, Desktop Commander, Cloudflare MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Stop your AI agent from breaking your API: OpenAPI contract checks and breaking-change diffs over MCP, fully local.
Local-first guardrails for AI coding agents working with OpenAPI specs: catch contract errors (missing operation IDs, unresolved references, public auth), detect breaking changes (removed operations, new required parameters, changed authentication), and keep API consumers working before you ship.
Zero configuration. No API keys. No network. Runs entirely on your machine via the Model Context Protocol.
Cursor:
Or use the direct protocol link: cursor://anysphere.cursor-deeplink/mcp/install?name=api-guardian&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1jcC1hcGktZ3VhcmRpYW4iXX0=
Claude Code:
claude mcp add api-guardian -- npx -y mcp-api-guardian
Or if installed in the petrovicistefan/mcp-marketplace:
/plugin marketplace add petrovicistefan/mcp-marketplace
Claude Desktop:
Add to claude_desktop_config.json:
{
"mcpServers": { "api-guardian": { "command": "npx", "args": ["-y", "mcp-api-guardian"] } } }
Cursor:
Add to ~/.cursor/mcp.json:
{
"mcpServers": { "api-guardian": { "command": "npx", "args": ["-y", "mcp-api-guardian"] } } }
VS Code / GitHub Copilot:
Or manually create/edit .vscode/mcp.json:
{
"servers": { "api-guardian": { "type": "stdio", "command": "npx", "args": ["-y", "mcp-api-guardian"] } } }
Windsurf:
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "api-guardian": { "command": "npx", "args": ["-y", "mcp-api-guardian"] } } }
Zed:
Add to your Zed settings.json:
{
"context_servers": { "api-guardian": { "command": "npx", "args": ["-y", "mcp-api-guardian"] } } }
Direct npx (one-line test):
npx -y mcp-api-guardian
Found this MCP useful? [Star this repository](https://github.com/petrovicistefan/mcp-api-guardian)!
A GitHub star helps other developers discover the project and lets you save it for later. Thanks for supporting open source!
AI coding agents increasingly modify OpenAPI specs as they work on API features, documentation, and integrations. A single agent iteration can:
operationId that generated SDKs rely onAPI Guardian catches these before they break production. It provides two MCP tools your AI agent can call:
Fully local, read-only, zero dependencies. No telemetry, no API keys, no network calls.
API Guardian provides 2 MCP tools for validating OpenAPI 3.0.x and 3.1.x documents:
| Tool | Description | Inputs |
|---|---|---|
| `audit_openapi` | Static OpenAPI 3.0/3.1 lint and authentication declaration review. Does not call endpoints. | spec (object): OpenAPI document as JSON |
| `compare_openapi` | Find selected breaking changes between two OpenAPI documents; not exhaustive schema compatibility. | before (object): Original OpenAPI document after (object): Updated OpenAPI document |
audit_openapi({spec})Static contract checks on a single OpenAPI spec:
$ref references, missing info.title/info.version, invalid pathsoperationId, missing response definitions{param} placeholders must be declared as required path parameters$ref URLs (not fetched)Reports errors and warnings with severity, location, and actionable messages. Explicitly states coverage limits.
compare_openapi({before, after})Breaking-change detection between two OpenAPI spec versions:
Reports definite breaks (error) and potential compatibility issues (warning). Schema variance and composed schemas are not yet analyzed (see Limitations).
Prompt: "Audit the OpenAPI spec at api/openapi.json before I commit"
Your AI agent calls audit_openapi, catches a missing operation ID, and suggests a fix — before the PR.
Prompt: "Compare the OpenAPI spec on this branch to main and fail if there are breaking changes"
Your agent runs compare_openapi, detects a removed endpoint, and blocks the merge with an actionable report.
Prompt: "Check all OpenAPI specs in api/ for public endpoints without authentication"
Your agent audits each spec, flags public operations, and generates a security review checklist.
| Feature | MCP API Guardian | oasdiff | pb33f/openapi-changes | optic (archived) |
|---|---|---|---|---|
| MCP integration | ✅ Native MCP server | ❌ CLI only | ❌ CLI only | ❌ CLI only |
| AI agent friendly | ✅ JSON-RPC stdio, designed for agents | ⚠️ CLI output parsing | ⚠️ CLI output parsing | ⚠️ Archived |
| Fully local (no network) | ✅ Zero network calls | ✅ Offline | ✅ Offline | ⚠️ Cloud offering existed |
| Breaking-change detection | ✅ Core feature | ✅ Comprehensive (773 checks) | ✅ Comprehensive | ✅ (legacy) |
| Static contract linting | ✅ Core feature | ⚠️ Validation only | ⚠️ Change-focused | ⚠️ Traffic-focused |
| Git revision comparison | ❌ Planned | ✅ Built-in | ✅ Built-in | ✅ (legacy) |
| Schema compatibility | ❌ Planned | ✅ Full | ✅ Full | ✅ (legacy) |
| HTML/Markdown reports | ❌ JSON only | ✅ Multiple formats | ✅ Multiple formats | ✅ (legacy) |
| License | MIT | Apache 2.0 | GPL-3.0 / Commercial | MIT (archived) |
When to use API Guardian:
When to use alternatives:
API Guardian is a targeted linter, not a complete OpenAPI validator. Current limitations:
oneOf/anyOf/allOf composed schemas, and property-level breaking changes require a later releasecompare_openapiPublic endpoints may be intentional; warnings are not proof of a vulnerability. Reports explicitly state coverage limits.
git clone https://github.com/petrovicistefan/mcp-api-guardian.git
cd mcp-api-guardian npm test npm start
Add to an MCP client's configuration, replacing the absolute path:
{
"mcpServers": { "api-guardian": { "command": "node", "args": ["/absolute/path/mcp-api-guardian/src/server.js"] } } }
Requirements: Node.js 22+
Future releases will add:
oneOf/anyOf/allOf), request vs response variance$ref references with configurable allowlistsThe local stdio MCP server above stays fully useful without an account or network. Quotas are enforced only by a separate hosted HTTP process that reserves units on mcp-control-plane before running the same analysis core.
# Terminal 1 — control plane (see its README for ADMIN_TOKEN)
node --env-file=.env src/server.js # in mcp-control-plane
cp .env.example .env # set CONTROL_PLANE_URL npm run start:hosted
Bootstrap a customer key with the control-plane admin API (POST /v1/admin/accounts, POST /v1/admin/keys). Then:
| Method | Path | Body |
|---|---|---|
| GET | /health | Liveness |
| POST |
只显示了开头部分;其余内容请在仓库中阅读