OpenAPI

by gujord

59 stars

274 downloads

Not rated

GitHub Website

About

Automatically generates MCP tools from OpenAPI specifications, enabling direct access to third-party REST APIs with authentication, validation, and error handling capabilities.

Details

Author: gujord
Repository: gujord/OpenAPI-MCP
GitHub stars: 59
Downloads: 274
License: MIT License
Categories: Productivity, Developer Tools, Design, Workplace, File Management, AI, Frontend, Infrastructure, Other, API

- Modular Architecture: Clean separation of concerns with dedicated modules for authentication, request handling, and tool generation.
- Robust Error Handling: Comprehensive exception hierarchy with proper JSON-RPC error codes and structured error responses.
- Auto Metadata: Derives tool names, summaries, and schemas from the OpenAPI specification.
- Sanitized Tool Names: Ensures compatibility with MCP name constraints.
- Flexible Parameter Parsing: Supports query strings, JSON, and comma-separated formats with intelligent type conversion.
- Enhanced Parameter Handling: Automatically converts parameters to correct data types with validation.
- Extended Tool Metadata: Includes detailed parameter information, response schemas, and API categorization.
- CRUD Operation Detection: Automatically identifies and generates example prompts for Create, Read, Update, Delete operations.
- MCP-Compliant Streaming: Official MCP HTTP transport for real-time streaming with proper session management.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name OpenAPI

Command (node, npx, python, etc.) npx
Arguments
- Argument 1 mcp-remote
- Argument 2 http://127.0.0.1:8001/sse
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "/c",
                "npx",
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "/c",
                "npx",
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "/c",
                "npx",
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "/c",
                "npx",
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "/c",
                "npx",
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

From the repository

Option 1: Using uvx (Recommended)

uvx openapi-mcp-proxy

OPENAPI_URL="https://api.met.no/weatherapi/locationforecast/2.0/swagger" \ SERVER_NAME="weather" \ uvx openapi-mcp-proxy

Option 2: Using pip

pip install openapi-mcp-proxy
Quick Test (Norwegian Weather API)

bash

OPENAPI_URL="https://api.met.no/weatherapi/locationforecast/2.0/swagger" \
SERVER_NAME="weather" \
openapi-mcp



HTTP Transport (Recommended for Claude Desktop)

bash

1. Copy the provided configuration:

cp claude_desktop_config.json ~/Library/Application\ Support/Claude/claude_desktop_config.json

2. Start the weather server:

OPENAPI_URL="https://api.met.no/weatherapi/locationforecast/2.0/swagger" \

SERVER_NAME="weather" \

MCP_HTTP_ENABLED="true" \

MCP_HTTP_PORT="8001" \

openapi-mcp

3. Test in Claude Desktop:
- Ask: "What's the weather in Oslo tomorrow?"
- Claude will use the weather_get__compact tool automatically!

Quick start with Docker:

json
{
"mcpServers": {
"secure_api": {
"command": "full_path_to_openapi_mcp/venv/bin/python",
"args": ["full_path_to_openapi_mcp/src/openapi_mcp/fastmcp_server.py"],
"env": {
"SERVER_NAME": "secure_api",
"OPENAPI_URL": "https://api.example.com/openapi.json",
"API_USERNAME": "your_username",
"API_PASSWORD": "your_password"
},
"transport": "stdio"
}
}
}

json
{
"mcpServers": {
"oauth_api": {
"command": "full_path_to_openapi_mcp/venv/bin/python",
"args": ["full_path_to_openapi_mcp/src/openapi_mcp/fastmcp_server.py"],
"env": {
"SERVER_NAME": "oauth_api",
"OPENAPI_URL": "https://api.example.com/openapi.json",
"OAUTH_CLIENT_ID": "your_client_id",
"OAUTH_CLIENT_SECRET": "your_client_secret",
"OAUTH_TOKEN_URL": "https://api.example.com/oauth/token"
},
"transport": "stdio"
}
}
}



Copy the provided example configuration:

bash
cp claude_desktop_config.json ~/Library/Application\ Support/Claude/claude_desktop_config.json



Start both services:

bash

`weather_get__compact`

Weather forecast for coordinates. Parameters: lat (float), lon (float)

`weather_get__complete`

Detailed weather forecast. Parameters: lat (float), lon (float)

`weather_get__status`

Server status check.

`petstore_addPet`

Add a new pet to the store. Parameters: pet (object)

`petstore_findPetsByStatus`

Find pets by status. Parameters: status (string)

`petstore_getPetById`

Find pet by ID. Parameters: petId (string)

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "openapi": {
            "cwd": null,
            "env": {},
            "args": [
                "mcp-remote",
                "http://127.0.0.1:8001/sse"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Linux

{
    "cwd": null,
    "env": [],
    "args": [
        "mcp-remote",
        "http://127.0.0.1:8001/sse"
    ],
    "shell": false,
    "command": "npx"
}

Macos

{
    "cwd": null,
    "env": [],
    "args": [
        "mcp-remote",
        "http://127.0.0.1:8001/sse"
    ],
    "shell": false,
    "command": "npx"
}

Windows

{
    "cwd": null,
    "env": [],
    "args": [
        "/c",
        "npx",
        "mcp-remote",
        "http://127.0.0.1:8001/sse"
    ],
    "shell": false,
    "command": "cmd"
}

OpenAPI to Model Context Protocol (MCP)

Repo Size
Last Commit
Open Issues

The OpenAPI-MCP proxy translates OpenAPI specs into MCP tools, enabling AI agents to access external APIs without custom wrappers!

OpenAPI-MCP

Bridge the gap between AI agents and external APIs

The OpenAPI to Model Context Protocol (MCP) proxy server bridges the gap between AI agents and external APIs by dynamically translating OpenAPI specifications into standardized MCP tools, resources, and prompts. This simplifies integration by eliminating the need for custom API wrappers.

Built with FastMCP following official MCP patterns and best practices, the server provides:
- ✅ Official FastMCP Integration - Uses the latest FastMCP framework for optimal performance
- ✅ Proper MCP Transport - Supports stdio, SSE, and streamable HTTP transports
- ✅ Modular Architecture - Clean separation of concerns with dependency injection
- ✅ Production Ready - Robust error handling, comprehensive logging, and type safety

- Repository: https://github.com/gujord/OpenAPI-MCP

---

If you find it useful, please give it a ⭐ on GitHub!

---

Key Features

Core Functionality

- FastMCP Transport: Optimized for stdio, working out-of-the-box with popular LLM orchestrators. - OpenAPI Integration: Parses and registers OpenAPI operations as callable tools. - Resource Registration: Automatically converts OpenAPI component schemas into resource objects with defined URIs. - Prompt Generation: Generates contextual prompts based on API operations to guide LLMs in using the API. - Dual Authentication: Supports both OAuth2 Client Credentials flow and username/password authentication with automatic token caching. - MCP HTTP Transport: Official MCP-compliant HTTP streaming transport with JSON-RPC 2.0 over SSE. - Server-Sent Events (SSE): Legacy streaming support (deprecated - use MCP HTTP transport). - JSON-RPC 2.0 Support: Fully compliant request/response structure.

Advanced Features

- Modular Architecture: Clean separation of concerns with dedicated modules for authentication, request handling, and tool generation. - Robust Error Handling: Comprehensive exception hierarchy with proper JSON-RPC error codes and structured error responses. - Auto Metadata: Derives tool names, summaries, and schemas from the OpenAPI specification. - Sanitized Tool Names: Ensures compatibility with MCP name constraints. - Flexible Parameter Parsing: Supports query strings, JSON, and comma-separated formats with intelligent type conversion. - Enhanced Parameter Handling: Automatically converts parameters to correct data types with validation. - Extended Tool Metadata: Includes detailed parameter information, response schemas, and API categorization. - CRUD Operation Detection: Automatically identifies and generates example prompts for Create, Read, Update, Delete operations. - MCP-Compliant Streaming: Official MCP HTTP transport for real-time streaming with proper session management.

Developer Experience

- Configuration Management: Centralized environment variable handling with validation and defaults. - Comprehensive Logging: Structured logging with appropriate levels for debugging and monitoring. - Type Safety: Full type hints and validation throughout the codebase. - Extensible Design: Factory patterns and dependency injection for easy customization and testing.

🚀 Quick Start

Installation

Option 1: Using uvx (Recommended)
```bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

weather_get__compact

weather_get__complete

weather_get__status

petstore_addPet

petstore_findPetsByStatus

petstore_getPetById

Claude Desktop / Cursor

Linux

Macos

Windows

OpenAPI to Model Context Protocol (MCP)

Bridge the gap between AI agents and external APIs

Key Features

Core Functionality

Advanced Features

Developer Experience

🚀 Quick Start

Installation

Install

More like this

Time

Sentry

Github

Git

GitLab

Context 7

`weather_get__compact`

`weather_get__complete`

`weather_get__status`

`petstore_addPet`

`petstore_findPetsByStatus`

`petstore_getPetById`