mcpField
🤖
🤖 OpenAPI MCP Server

🤖 OpenAPI MCP Server

Local
npmjs.comDeveloper Tools7Updated 78w ago
RepositoryVisit website

About 🤖 OpenAPI MCP Server

OpenAPI MCP Server is a command-line tool that creates an MCP server from an OpenAPI specification and proxies requests to the corresponding REST API. It is for developers making existing OpenAPI services available to MCP clients; the project is in early development.

Key features

  1. 01Generate an MCP server from OpenAPI
  2. 02Proxy requests to a REST API
  3. 03Translate between MCP and REST conventions
  4. 04Configure spec, target URL, and port

Use cases

  1. 01Making an existing OpenAPI service available to MCP clients
  2. 02Calling REST APIs through an MCP client
  3. 03Running an MCP server for a specified API

MCP support

It generates an MCP server from an OpenAPI specification and forwards MCP client requests to the target REST API.

#cli#rest#server#proxy#mcp#openapi

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "openapi-mcp-proxy": {
      "command": "npx",
      "args": [
        "-y",
        "openapi-mcp-proxy"
      ]
    }
  }
}
Run commandnpx -y openapi-mcp-proxy

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmopenapi-mcp-proxy

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🤖 OpenAPI MCP Server

asciicast

A command-line tool that transforms any OpenAPI service into a Model Context Protocol (MCP) server, enabling seamless integration with AI agents and tools that support the MCP specification.

Note

This tool is still in early development stage. Roadmap is here

What is Model Context Protocol (MCP)?

Model Context Protocol (MCP) is a standardized protocol for AI agents to interact with external tools and services. It provides a consistent way for AI models to discover, understand, and utilize various capabilities through a unified interface, making it easier to build AI-powered applications that can interact with multiple services.

What is OpenAPI?

OpenAPI (formerly known as Swagger) is a specification for machine-readable interface files for describing, producing, consuming, and visualizing RESTful web services. It allows both humans and computers to discover and understand the capabilities of a service without needing to access the source code or additional documentation.

About This Project

This middleware acts as a bridge between OpenAPI services and MCP clients. It:

  1. Takes an OpenAPI specification file as input
  2. Automatically generates an MCP-compliant server
  3. Proxies incoming requests to the actual OpenAPI service
  4. Translates between MCP and REST conventions

This enables any existing REST API with an OpenAPI specification to be immediately accessible to AI agents that understand MCP, without requiring any modifications to the original service.

Installation

npm install -g openapi-mcp-proxy

Usage

npx openapi-mcp-proxy --spec ./path/to/openapi.yml --target http://your-api.com --port 3000
Options
  • -s, --spec <path> (required): Path to your OpenAPI specification file (env: OMP_OPENAPI_SPEC_FILE)
  • -t, --target <url> (optional): Target URL of the API service (default: "http://localhost:8080", env:OMP_TARGET_BASE_URL)
  • -p, --port <number> (optional): Port to run the MCP server on (default: "3000", env: PORT)
  • -V, --version: Display version number
  • -h, --help: Display help for command
Example

Start an MCP server for the Petstore API

npx openapi-mcp-proxy --spec resources/petstore.openapi.yml --target https://petstore.swagger.io/v2
Testing
MCP Inspector

To test your MCP server, you can use the Model Context Protocol:

  1. Install the MCP Inspector:
npx @modelcontextprotocol/inspector
  1. Start your MCP server
  2. Navigate to the inspector's UI and fill in the correct server path ending with /mcp like http://localhost:3000/mcp
  3. Now you can interact with your MCP server. The MCP Inspector will show you detailed information about the requests and responses.
with VS Code

It's easier to use this with VS Code's built-in agent mode:

  1. Open VS Code and enable agent mode:
    • Press Cmd/Ctrl + Shift + P
    • Type "Toggle GitHub Copilot Agent Mode"
    • Select "Enable"
  2. Add your MCP server:
    • Press Cmd/Ctrl + Shift + P
    • Type "MCP: add Server"
    • type your MCP server URL like http://localhost:3000/mcp ending with /mcp
  3. Your github copilot chat should pick up on the new tools it has!
  4. Now you can interact with your MCP server through VS Code's agent interface. Try asking it "how many pets are available right now?"

for more information on how to use MCP servers with VS code, see this

Contributing

Contributions are welcome! Please feel free to submit a Pull Request. Roadmap is here

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.