
Swagger Explorer MCP
A Management Control Plane server that allows users to explore and analyze Swagger/OpenAPI specifications, providing features such as endpoint exploration, schema analysis, and customizable response formatting, with support for authentication and integration with tools like Claude.
README
Swagger Explorer MCP
A Management Control Plane (MCP) server for exploring and analyzing Swagger/OpenAPI specifications through Claude.
Quick Start
Install and run globally using npx:
npx -y @johnneerdael/swagger-mcp
Or install with environment variables:
npx -y @johnneerdael/swagger-mcp \
--env BASE_URL=/api \
--env AUTH_TOKEN=your-token \
--env PORT=3000
Installation for Claude Desktop
- Open Claude Desktop
- Click on Settings (gear icon)
- Select "Tools & Integrations"
- Click "Add MCP Server"
- Enter the following:
Name: Swagger Explorer Command: npx -y @johnneerdael/swagger-mcp Arguments: --swagger-url=$SWAGGER_URL
- Click "Install"
Usage with Claude
Here are some example interactions with Claude:
Basic Swagger Exploration
Human: Can you explore the Swagger documentation at http://localhost:8080/docs?
Claude: I'll help you explore that Swagger documentation using the Swagger Explorer MCP.
Let me analyze the API endpoints and schemas for you:
[Claude would then use the MCP to fetch and analyze the Swagger documentation]
Analyzing Specific Endpoints
Human: What are the available response schemas for the /pets POST endpoint?
Claude: I'll check the response schemas for that endpoint using the MCP.
[Claude would use the MCP to fetch specific endpoint details]
Schema Analysis
Human: Can you show me the detailed structure of the Pet schema?
Claude: I'll retrieve the detailed schema information using the MCP.
[Claude would use the MCP to analyze the schema structure]
Features
-
Authentication Support
- Bearer token authentication
- Configurable through environment variables
-
Custom Response Formatting
- Minimal format: Removes null/empty values
- Detailed format: Includes metadata and timestamps
- Raw format: Unmodified response
-
Schema Analysis
- Detailed property exploration
- Response schema analysis
- Schema relationships
-
API Exploration
- Path listing
- Method filtering
- Response format analysis
Configuration
Environment Variables:
BASE_URL
: Base path for the API (default: '')AUTH_TOKEN
: Bearer token for authenticationPORT
: Server port (default: 3000)SWAGGER_URL
: Default Swagger documentation URL
API Endpoints
Explore API
curl -X POST http://localhost:3000/api/explore \
-H "Authorization: Bearer your-token" \
-H "Content-Type: application/json" \
-d '{
"url": "http://your-swagger-url",
"options": {
"paths": true,
"schemas": true
}
}'
Get Schema Details
curl -X POST http://localhost:3000/api/schema-details \
-H "Authorization: Bearer your-token" \
-H "Content-Type: application/json" \
-d '{
"url": "http://your-swagger-url",
"schemaName": "Pet"
}'
Get Response Schemas
curl -X POST http://localhost:3000/api/response-schemas \
-H "Authorization: Bearer your-token" \
-H "Content-Type: application/json" \
-d '{
"url": "http://your-swagger-url",
"path": "/pets",
"method": "post"
}'
Response Formats
Minimal Format
{
"status": "success",
"data": {
// Only non-null values
}
}
Detailed Format
{
"status": "success",
"timestamp": "2025-01-29T10:00:00.000Z",
"data": {
// Full response
},
"metadata": {
"version": "1.0",
"format": "detailed"
}
}
Common Use Cases
-
API Documentation Review
Human: Can you summarize all the available endpoints and their purposes?
-
Schema Validation
Human: What fields are required for creating a new pet?
-
Response Analysis
Human: What are the possible error responses for the login endpoint?
-
Integration Planning
Human: How should I structure my request to create a new order?
Troubleshooting
-
Connection Issues
- Ensure the Swagger URL is accessible
- Check if authentication token is correct
- Verify port is not in use
-
Authorization Errors
- Verify AUTH_TOKEN is set correctly
- Ensure bearer token is included in requests
-
Schema Not Found
- Check if schema name is exact match
- Verify Swagger spec is loaded correctly
Security Notes
- The MCP requires authentication if AUTH_TOKEN is set
- All requests are logged for debugging
- Sensitive information is not cached
- Rate limiting is applied to prevent abuse
Development
To contribute or modify:
- Clone the repository
- Install dependencies:
npm install
- Build:
npm run build
- Run locally:
npm start
License
MIT License - See 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.