openapi-mcp-swagger

Overview

This MCP server transforms complex API documentation into an intelligent, searchable knowledge base that AI assistants can query directly. Instead of struggling with large API docs that exceed context windows, developers can now have natural conversations about their APIs. The server indexes Swagger/OpenAPI specs and provides fast, relevant responses to queries about endpoints, parameters, and schemas. It supports large API files (10MB+) and includes production features like authentication and monitoring.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• searchEndpoints

  Search for API endpoints using natural language keywords

  Try:Find user management endpointsTry:Show me payment processing APIsTry:What endpoints handle authentication?
• getEndpointDetails

  Get detailed information about a specific API endpoint

  Try:Show me details for POST /usersTry:Get parameters for the payment endpointTry:What's the response schema for GET /products?
• generateCodeExample

  Generate code examples for using API endpoints

  Try:Generate Python code for user creationTry:Show me how to call the payment API in JavaScriptTry:Give me a cURL example for the product endpoint
• listSchemas

  List all data schemas defined in the API specification

  Try:Show me all user-related schemasTry:List all payment schemasTry:What schemas are available for products?
• getSchemaDetails

  Get detailed information about a specific data schema

  Try:Show me the User schema detailsTry:What fields are in the Order schema?Try:Get details for the PaymentMethod schema

Comparable tools

Installation

# Install from source
git clone https://github.com/salacoste/openapi-mcp-swagger.git
cd openapi-mcp-swagger
pip install -r requirements.txt

# Convert Swagger file to MCP server
swagger-mcp-server convert swagger-openapi-data/your-api.json --name your-api

cd mcp-server-your-api
swagger-mcp-server serve

# For Claude Desktop, add to Claude's config.json:
{
  "mcpServers": {
    "your-api": {
      "command": "swagger-mcp-server",
      "args": ["serve", "--port", "8080"]
    }
  }
}```

FAQ

What size of API docs can this handle?

The server can process OpenAPI files up to 10MB+ using stream-based parsing to handle large specifications efficiently.

Which AI assistants are compatible?

Works with any MCP-compatible tool including Claude, Cursor, VS Code, and custom implementations through the standard MCP protocol.

Compare openapi-mcp-swagger with