Baryhuang MCP Server Any Openapi

🚀 MCP Server

The MCP Server is a FastAPI - based service that supports the MCP protocol integrated with Claude Desktop. It offers the ability to understand and invoke APIs through natural language processing. The server can parse OpenAPI specifications, generate semantic indexes, and recommend suitable API endpoints based on users' natural - language queries.

🚀 Quick Start

The MCP Server provides the ability to understand and call APIs through natural language processing. It can parse OpenAPI specifications, generate semantic indexes, and recommend appropriate API endpoints according to users' natural language queries.

✨ Features

• OpenAPI Parsing: Supports parsing standard OpenAPI 3.x specifications and can handle large specification files containing thousands of endpoints.
• Semantic Search: Utilizes optimized embedding models (such as sentence - transformers) to generate semantic representations for each API endpoint and match them against users' natural - language queries.
• Automatic Recommendation: Recommends the most relevant API endpoints, request methods, and parameter information based on semantic similarity.
• Documentation Generation: Can automatically generate structured API documentation, including detailed information such as paths, methods, parameters, and response formats.

📦 Installation

Using the Pre - built Image

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

Local Development Build

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

Starting 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

Key Components

1. EndpointSearcher: The core class responsible for:
   • Parsing OpenAPI specifications.
   • Creating semantic search indexes.
   • Formatting endpoint documentation.
   • Handling natural - language queries.
2. Server Implementation:
   • An asynchronous FastAPI server.
   • Support for the MCP protocol.
   • Tool registration and invocation processing.

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",
        "buryhuang/mcp-server-any-openapi:latest"
      ]
    }
  }
}

Implementation Notes

• Endpoint - based Processing: Different from document - based holistic analysis, we generate a unique identifier for each endpoint in the following ways:
  • Path + Method
  • Parameter - aware embedding
  • Response schema context
• Optimized Specification Processing: Process OpenAPI specifications (supports specifications up to 10MB with approximately 5,000 endpoints) in the following ways:
  • Lazy - loading of schema components
  • Parallel parsing of path items
  • Selective generation of embeddings (ignoring 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. Open a Pull Request.

📄 License

This project is licensed under the terms in the LICENSE file.