📌Overview

Purpose: swagger-mcp aims to dynamically generate MCP tools from Swagger UI by scraping the swagger.json file, facilitating tool selection for MCP clients.

Overview: swagger-mcp simplifies the integration of Swagger UI with MCP clients by automatically generating well-defined tools at runtime. This enhances the user experience and streamlines the utilization of APIs.

Key Features:

Dynamic Tool Generation: Automatically generates MCP tools at runtime from swagger.json, ensuring quick and efficient tool access.
Integration with MCP Clients: Easily integrates with any MCP client, enhancing its functionality to support various use cases.

swagger-mcp

Overview

swagger-mcp is a tool designed to scrape Swagger UI by extracting the swagger.json file and dynamically generating well-defined MCP tools at runtime. These tools can be utilized by the MCP client for further tool selection.

Demo Video

Check out the demo video showcasing the project in action:

Support

If you find this project valuable, please support me on LinkedIn by:

Liking and sharing the demo post
Leaving your thoughts and feedback in the comments
Connecting with me for future updates

Your support will help reach more people and improve the project!

Prerequisites

To use swagger-mcp, ensure you have the following dependencies:

LLM Model API Key / Local LLM: Requires access to OpenAI, Claude, or Ollama models.
Any MCP Client: Used mcphost from mark3labs.

Installation and Setup

Install and run swagger-mcp with:

go install github.com/danishjsheikh/swagger-mcp@latest
swagger-mcp

MCP Configuration

To integrate with mcphost, include the following configuration in .mcp.json:

{
    "mcpServers":
    {
        "swagger_loader": {
            "command": "swagger-mcp",
            "args": ["--specUrl=<swagger/doc.json_url>"]
        }
    }
}

Demo Flow

Run the backend demo:

go install github.com/danishjsheikh/go-backend-demo@latest 
go-backend-demo

Run Ollama:
```
ollama run llama3.2
```

Run MCP Client:

go install github.com/mark3labs/mcphost@latest
mcphost -m ollama:llama3.2 --config <.mcp.json_file_path>

Need Help

Work is ongoing to improve tool definitions to enhance:

Better error handling for more accurate responses
LLM behavior control to ensure reliance only on API responses without using its own memory
Preventing hallucinations and random data generation by enforcing strict data retrieval from APIs

If you have insights or suggestions on improving these aspects, please contribute by:

Sharing your experience with similar implementations
Suggesting modifications to tool definitions
Providing feedback on current limitations

Your input will be invaluable in making this tool more reliable and effective! 🚀