MCP Server Any Openapi

🚀 MCP Server

The MCP (Message Communication Protocol) Server, based on FastAPI, is designed to support interactions with Claude Desktop. It can be run via Docker and supports multi - platform architectures.

🚀 Quick Start

The MCP Server is a protocol implementation based on FastAPI, enabling interaction with Claude Desktop. It can be run using Docker and supports multiple platform architectures.

✨ Features

• Multi - architecture Support: The official image supports three platforms: linux/amd64, linux/arm64.
• Flexible Tool Naming: The tool name can be controlled via MCP_API_PREFIX.
• OpenAPI Support: It can handle OpenAPI specifications, extract API endpoint information, and provide search functionality.

📦 Installation

Using the Pre - built Image (Docker Hub)

docker pull buryhuang/mcp-server-any-openapi:latest

Local Development Build

docker build -t mcp-server-any-openapi .

Running the Container

docker run \
  -e OPENAPI_JSON_DOCS_URL=https://api.example.com/openapi.json \
  -e MCP_API_PREFIX=finance \
  buryhuang/mcp-server-any-openapi:latest

🔧 Technical Details

Core Components

1. EndpointSearcher: The core class that handles the following functions:

   • Parsing of OpenAPI specifications
   • Creation of semi - retrieval indexes
   • Formatting of endpoint documents
   • Handling of natural language queries

2. Server Implementation:

   • An asynchronous FastAPI server
   • Support for the MCP protocol
   • Handling of tool registration and invocation

Integration and Configuration

Configure the MCP Server in Claude Desktop:

{
  "mcpServers": {
    "any_openapi": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAPI_JSON_DOCS_URL=https://api.example.com/openapi.json",
        "-e",
        "MCP_API_PREFIX=finance",
        "-e",
        "GLOBAL_TOOL_PROMPT='Access to insights apis for ACME Financial Services abc.com .",
        "buryhuang/mcp-server-any-openapi:latest"
      ]
    }
  }
}

Implementation Notes

• Endpoint - based Processing: Different from document - based methods that struggle with large - scale documents, we index endpoints in the following ways:
  • Use paths and methods as unique identifiers
  • Parameter - aware embeddings
  • Response scheme context
• Optimized Specification Processing: Handle OpenAPI specifications (supporting up to 10MB or approximately 5,000 endpoints) in the following ways:
  • Lazy - loading component mode
  • Parallel parsing of path items
  • Selective generation of embeddings (omitting redundant descriptions)

🤝 Contribution Guidelines

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing - feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing - feature)
5. Submit a Pull Request

📄 License

The project includes its license terms in the LICENSE file.