swagger-api-mcp-server
Parses Swagger 2.0 and OpenAPI 3.x specifications, exposing API endpoints, schemas, and authentication through MCP tools with local caching to reduce token usage.
README
Swagger API MCP Server
An MCP (Model Context Protocol) server that parses Swagger 2.0 and OpenAPI 3.x specifications, exposing API structure through MCP tools. Features a local file-cache architecture that reduces token usage by 85-95% compared to inline responses.
Features
- Swagger 2.0 & OpenAPI 3.x — Full dual-format support
- Smart Caching — Spec parsed once, stored as local JSON files; tools return compact summaries + file paths (~200 chars vs 5-20KB)
- 11 MCP Tools — Load, browse, search, call APIs, and manage auth dynamically
- 3 MCP Prompts — Guided workflows for exploring, searching, and integrating APIs
- 3 MCP Resources — Direct access to cached API info, endpoints, and schemas
- Two Transport Modes — stdio (for CLI/IDE integration) and HTTP (for multi-session web use)
- 2-Phase API Calls — Preview requests before executing them
- Zero External Parsers — Custom
$refresolver with circular reference protection
Prerequisites
- Node.js >= 24
Quick Start
Install from npm
npm install -g swagger-api-mcp-server
Or clone and build
git clone https://github.com/NekoTarou/swagger-api-mcp-server.git
cd swagger-api-mcp-server
npm install
npm run build
Run
# stdio mode (default) — for MCP clients like Claude Desktop
npm start
# Auto-load a spec on startup
SWAGGER_URL=https://petstore.swagger.io/v2/swagger.json npm start
# HTTP mode — multi-session with Express
npm run start:http
MCP Client Configuration
Claude Desktop
Add to your Claude Desktop config file (claude_desktop_config.json):
{
"mcpServers": {
"swagger-api": {
"command": "npx",
"args": ["-y", "swagger-api-mcp-server"],
"env": {
"SWAGGER_URL": "https://petstore.swagger.io/v2/swagger.json"
}
}
}
}
Cursor / VS Code
Add to your MCP settings:
{
"mcpServers": {
"swagger-api": {
"command": "npx",
"args": ["-y", "swagger-api-mcp-server"],
"env": {
"SWAGGER_URL": "https://your-api.example.com/openapi.json"
}
}
}
}
Tools
| Tool | Description |
|---|---|
swagger_load_spec |
Load a Swagger/OpenAPI spec from URL, parse and cache it |
swagger_update_cache |
Re-fetch spec and rebuild cache |
swagger_get_info |
Get API metadata (title, version, servers, auth schemes) |
swagger_list_tags |
List all tags with endpoint counts |
swagger_list_paths |
List endpoints with filtering (tag, method, keyword) and pagination |
swagger_get_endpoint |
Get endpoint summary + cached file path for full details |
swagger_list_schemas |
List schema definitions with filtering and pagination |
swagger_get_schema |
Get schema summary + cached file path for full definition |
swagger_search |
Search across endpoints and schemas by keyword |
swagger_call_api |
Execute HTTP requests with 2-phase confirmation |
swagger_set_auth |
Dynamically set or clear the Authorization header at runtime |
Prompts
| Prompt | Arguments | Description |
|---|---|---|
swagger_explore_api |
url |
Guided workflow to load and fully explore an API spec |
swagger_find_endpoint |
keyword |
Search for endpoints by keyword and view full details |
swagger_integrate_api |
url, task |
Find the right endpoint for a task and execute an API call |
Resources
| Resource | URI | Description |
|---|---|---|
api-info |
swagger://api/info |
API basic information (title, version, servers, auth) |
api-endpoints |
swagger://api/endpoints |
Index of all API endpoints |
api-schemas |
swagger://api/schemas |
Index of all schema/model definitions |
Cache Architecture
When a spec is loaded, it's parsed once and stored as structured JSON files:
.swagger-cache/
├── meta.json # Cache metadata (URL, counts, timestamp)
├── info.json # Full API info (title, servers, auth)
├── tags.json # Tag list with endpoint counts
├── paths-index.json # Endpoint index for fast lookup
├── schemas-index.json # Schema index for fast lookup
├── endpoints/ # One file per endpoint (deep-resolved)
│ └── GET__users__{id}.json
└── schemas/ # One file per schema (deep-resolved)
└── User.json
Tools return brief summaries with file paths. The LLM reads full details on demand via the Read tool — saving 85-95% of tokens per call.
Environment Variables
| Variable | Default | Description |
|---|---|---|
SWAGGER_URL |
(empty) | Auto-load spec on startup |
TRANSPORT |
stdio |
Transport mode: stdio or http |
MCP_PORT |
3000 |
HTTP server port |
MCP_HOST |
0.0.0.0 |
HTTP server host |
API_BASE_URL |
(empty) | Override API base URL for calls |
API_AUTH_TOKEN |
(empty) | Initial Authorization header value (can be updated at runtime via swagger_set_auth) |
CACHE_DIR |
.swagger-cache |
Custom cache directory path |
SESSION_TIMEOUT_MS |
1800000 |
HTTP session timeout (30 min) |
MAX_SESSIONS |
100 |
Max concurrent HTTP sessions |
Development
npm run dev # Dev mode with auto-reload (tsx watch)
npm test # Run tests
npm run build # TypeScript compilation → dist/
npm run clean # Remove dist/
License
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。