OpenAPI MCP server

This MCP server allows you to expose REST APIs as context to Large Language Models (LLMs), enabling them to interact with and execute API calls based on natural language prompts. The server supports HTTP methods including GET, PUT, POST, and PATCH.

Installation

Basic Setup

Install the package using pip:

pip install openapi_mcp_server

Create a .env file in your project folder with the required configuration:

OPENAPI_SPEC_PATH=https://petstore.swagger.io/v2/swagger.json
API_BASE_URL=https://petstore.swagger.io/v2

Start the server from the folder containing your .env file:

uv run openapi_mcp_server

Configuration Options

Environment Variables

The server can be configured using the following environment variables:

• DEBUG: Enable debug logging (optional, defaults to False)
• OPENAPI_SPEC_PATH: Path to the OpenAPI document (required)
• API_BASE_URL: Base URL for the API requests (required)
• API_HEADERS: Headers to include in API requests (optional)
• API_WHITE_LIST: Comma-separated list of allowed operation IDs (optional)
• API_BLACK_LIST: Comma-separated list of blocked operation IDs (optional)
• HTTP_PROXY: HTTP Proxy details (optional)
• HTTPS_PROXY: HTTPS Proxy details (optional)
• NO_PROXY: No Proxy details (optional)

Integration with Claude Desktop

Claude Desktop Configuration

To integrate the MCP server with Claude Desktop, add the following configuration:

{
  "mcpServers": {
    "openapi_mcp_server": {
      "command": "uv",
      "args": ["run", "openapi_mcp_server"],
      "env": {
        "DEBUG": "1",
        "API_BASE_URL": "https://petstore.swagger.io/v2",
        "OPENAPI_SPEC_PATH": "https://petstore.swagger.io/v2/swagger.json",
        "API_HEADERS": "Accept:application/json",
        "API_WHITE_LIST": "addPet,updatePet,findPetsByStatus"
      }
    }
  }
}

This configuration allows Claude to access and interact with the specified Pet Store API endpoints.

Example Use Cases

Pet Store API Example

With the above configuration, you can ask Claude to perform actions like:

• Finding pets by their status
• Adding new pets to the store
• Updating existing pet information

The LLM will handle the conversion from natural language to the appropriate API calls using the MCP server as an intermediary.

Troubleshooting

If you encounter issues:

1. Enable debug mode by setting DEBUG=1 in your environment variables
2. Verify your API endpoint is accessible
3. Check that your OpenAPI specification path is correct
4. Ensure any required authentication details are included in API_HEADERS

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "openapi_mcp_server" '{"command":"uv","args":["run","openapi_mcp_server"],"env":{"DEBUG":"1","API_BASE_URL":"https://petstore.swagger.io/v2","OPENAPI_SPEC_PATH":"https://petstore.swagger.io/v2/swagger.json","API_HEADERS":"Accept:application/json","API_WHITE_LIST":"addPet,updatePet,findPetsByStatus"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "openapi_mcp_server": {
            "command": "uv",
            "args": [
                "run",
                "openapi_mcp_server"
            ],
            "env": {
                "DEBUG": "1",
                "API_BASE_URL": "https://petstore.swagger.io/v2",
                "OPENAPI_SPEC_PATH": "https://petstore.swagger.io/v2/swagger.json",
                "API_HEADERS": "Accept:application/json",
                "API_WHITE_LIST": "addPet,updatePet,findPetsByStatus"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "openapi_mcp_server": {
            "command": "uv",
            "args": [
                "run",
                "openapi_mcp_server"
            ],
            "env": {
                "DEBUG": "1",
                "API_BASE_URL": "https://petstore.swagger.io/v2",
                "OPENAPI_SPEC_PATH": "https://petstore.swagger.io/v2/swagger.json",
                "API_HEADERS": "Accept:application/json",
                "API_WHITE_LIST": "addPet,updatePet,findPetsByStatus"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect