Swagger Navigator MCP Server
Enables AI assistants to discover, search, and interact with REST APIs by parsing OpenAPI/Swagger specifications with intelligent fuzzy search across endpoints, supporting both local and remote API sources.
README
๐ Swagger Navigator MCP Server
An MCP server implementation that provides intelligent discovery and search capabilities for Swagger/OpenAPI endpoints. This tool enables AI assistants to dynamically explore, understand, and interact with REST APIs by parsing OpenAPI specifications and providing fuzzy search across endpoints.
๐ How It Works
The Swagger Navigator MCP Server acts as an intelligent API knowledge hub, seamlessly connecting developers with their API specifications. When you ask Cursor/Claude/LLMs to generate API clients, anticorruption layers, or type definitions, Cursor/Claude/LLMs consults the MCP server to get accurate, structured API information and then generates perfect code based on the actual API schema.
flowchart TD
A[๐จโ๐ป Developer] -->|"๐ฌ Generate API client<br/>for /users endpoint"| B[๐ฏ Cursor/IDE/LLMs]
B -->|"๐ Query: What is<br/>/users endpoint?"| C[๐ Swagger Navigator MCP Server]
C -->|"๐ Returns endpoint<br/>schema & structure"| B
B -->|"โจ Here's your<br/>generated API client"| A
style A fill:#74b9ff,stroke:#0984e3,stroke-width:2px,color:#fff
style B fill:#a29bfe,stroke:#6c5ce7,stroke-width:2px,color:#fff
style C fill:#ff6b6b,stroke:#333,stroke-width:4px,color:#fff
linkStyle 0 stroke:#fd79a8,stroke-width:3px
linkStyle 1 stroke:#00b894,stroke-width:3px
linkStyle 2 stroke:#fdcb6e,stroke-width:3px
linkStyle 3 stroke:#e17055,stroke-width:3px
โจ Features
- ๐ Dynamic API Discovery: Automatically parse and index Swagger/OpenAPI specifications from multiple sources
- ๐ฏ Intelligent Search: Use fuzzy matching to find relevant endpoints based on natural language queries
- ๐ Multi-source Support: Handle both local files and remote HTTP endpoints with authentication
- โก Real-time Updates: Monitor configuration changes and refresh API data automatically
- ๐ Hot-reload Configuration: Detect config file changes without server restart
๐ ๏ธ Tools
๐ list_all_sources
Retrieves a comprehensive list of all available Swagger/OpenAPI sources in the system.
Purpose:
- Provides overview of all loaded API specifications
- Shows available APIs for search and exploration
- Returns source names for use with other tools
Returns:
- Array of sources with name, description, and OpenAPI info (title, version)
๐ list_endpoints_for_source
Retrieves all endpoints from a specific API source with pagination support.
Inputs:
name(string): The source name to list endpoints forlimit(number, optional): Maximum endpoints to return (1-100, default: 10)offset(number, optional): Number of endpoints to skip (default: 0)
Returns:
- Array of endpoints with path, method, description, and metadata
- Pagination information with total count and navigation flags
๐ search_endpoint
Intelligently searches endpoints using fuzzy matching across multiple attributes.
Inputs:
query(string): Search query using natural language (e.g., "create user", "authentication", "GET users")
Returns:
- Ranked array of matching endpoints with relevance scores
- Weighted search across descriptions, paths, methods, and tags
โ๏ธ Configuration
๐ค Usage with Cursor
Add this to your ~/.cursor/mcp.json:
Using npx
{
"mcpServers": {
"swagger-navigator-mcp": {
"command": "npx",
"args": ["-y", "swagger-navigator-mcp"],
"env": {
"CONFIG_PATH": "path/to/swagger-navigator-mcp.config.yaml"
}
}
}
}
๐ Configuration File
Create a swagger-navigator-mcp.config.yaml file:
# Swagger Navigator MCP Server Configuration
sources:
# Local file example
- name: "petstore-local"
source: "./specs/petstore.json"
description: "Local Petstore API specification"
# Remote HTTP source with authentication
- name: "github-api"
source: "https://api.github.com"
description: "GitHub REST API v3"
headers:
Authorization: "token ${GITHUB_TOKEN}"
Accept: "application/vnd.github.v3+json"
# API with custom headers
- name: "internal-api"
source: "https://internal.company.com/api/swagger.json"
description: "Internal company API"
headers:
X-API-Key: "${API_KEY}"
# Optional: Search configuration
search:
fuzzyThreshold: 0.6 # 0-1, lower = more fuzzy matching
# Optional: Refresh interval in seconds
refreshInterval: 300 # Refresh every 5 minutes
๐ Environment Variable Substitution
The configuration file supports environment variable substitution using ${VARIABLE_NAME} syntax. This allows you to securely store sensitive information like API keys and tokens outside of your configuration file.
Examples:
${GITHUB_TOKEN}- Substituted with the value of theGITHUB_TOKENenvironment variable${API_KEY}- Substituted with the value of theAPI_KEYenvironment variable${DATABASE_URL}- Any environment variable can be used
Note: If an environment variable is not set, the substitution will result in an empty string.
๐ Environment Variables
Set environment variables for configuration and authentication:
export CONFIG_PATH="./swagger-navigator-mcp.config.yaml"
export GITHUB_TOKEN="your-github-token"
export API_KEY="your-api-key"
๐ Usage
๐ฆ Install Dependencies
npm install
๐จ Build the Project
npm run build
โถ๏ธ Start the Server
CONFIG_PATH=./swagger-navigator-mcp.config.yaml npm start
๐งช Development Mode
npm run dev
๐ License
This project is licensed under the ISC License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.