Openapi2mcpserver

🚀 OpenAPI to MCP Server

This project enables you to set up a Model Context Protocol (MCP) server directly from the provided openapi.yaml using uv for dependency management. Each HTTP endpoint is transformed into an MCP tool that AnythingLLM (or any MCP-aware client) can invoke.

🚀 Quick Start

📦 Install dependencies

uv sync

⚙️ Configure openapi2mcpserver/config.yaml

base_url: "https://localhost:12001"
verify_ssl: false
openapi_path: "../openapi.yaml"           # Optional, defaults to the repo root copy
log_file: "../logs/openapi2mcpserver.log" # Optional, enables file logging
log_level: "INFO"                         # Optional, supports DEBUG/INFO/WARNING/ERROR

auth:
  mode: "basic"                           # Options: none/basic/bearer/header/query
  username: "your-username"
  password: "your-password"
  # basic_token: "cHJlLWVuY29kZWQtY3JlZHM="
  # extra_headers:
  #   X-API-Version: "1"

# default_headers:
#   X-Request-Source: "mcp"

▶️ Start the MCP server

uv run openapi2mcpserver

💻 Usage Examples

Using This MCP Server in AnythingLLM

The following steps are for the AnythingLLM desktop plugin system, listing the default paths for macOS and Windows. Create the file if it doesn't exist and replace the sample paths with the actual values on your machine.

🍎 macOS

1. Open ~/Library/Application Support/anythingllm-desktop/storage/plugins/anythingllm_mcp_servers.json
2. Add or merge the following configuration:

{
  "mcpServers": {
    "rhino-agent": {
      "command": "/Users/<your_username>/.local/bin/uv",
      "args": ["run", "--project", "/Users/<your_username>/workspace/AIProjects/openapi2mcpserver", "openapi2mcpserver"]
    }
  }
}

🪟 Windows

1. Open %APPDATA%\anythingllm-desktop\storage\plugins\anythingllm_mcp_servers.json
2. If you use uv.exe, replace the path with the output of where uv, for example:

{
  "mcpServers": {
    "rhino-agent": {
      "command": "C:\\Users\\<YourUser>\\AppData\\Roaming\\Python\\Scripts\\uv.exe",
      "args": ["run", "--project", "C:\\Users\\<YourUser>\\workspace\\AIProjects\\openapi2mcpserver", "openapi2mcpserver"]
    }
  }
}

After saving, restart AnythingLLM (or reload plugins in settings), and you should see rhino-agent available in the tool list for your workspace.

✨ Features

• Automatically parses every OpenAPI path and registers a matching MCP tool
• Exposes OpenAPI_GetSchema to inspect components.schemas
• Tool inputs cover path params, query params, headers, and request bodies
• Flexible authentication (none/basic/bearer/custom header/query) plus global default headers
• Structured logging to both console and file for easier LLM troubleshooting

📁 Layout

openapi2mcpserver/
    __init__.py
    __main__.py
    client.py
    config.py
    openapi_loader.py
    server.py

🔧 Technical Details

At startup, the server ingests the OpenAPI description, builds JSON Schema input for every tool, and forwards calls to the upstream API. Responses (status, headers, and JSON/text bodies) are returned verbatim to the MCP client so you can chain follow-up actions such as polling task status.