MCP Adapter

v1.0.0โ€ขAPIsโ€ขstable

Automatically converts OpenAPI specifications into Model Context Protocol applications, enabling HTTP APIs to be managed as MCP services. It features a dynamic architecture that monitors file systems or Kubernetes ConfigMaps to update MCP tools in re

adapterhttpllmmcpmcp-tools
Share:
1,127
Stars
0
Downloads
0
Weekly
0/5

What is MCP Adapter?

MCP Adapter is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to automatically converts openapi specifications into model context protocol applications, enabling http apis to be managed as mcp services. it features a dynamic architecture that monitors file systems ...

Automatically converts OpenAPI specifications into Model Context Protocol applications, enabling HTTP APIs to be managed as MCP services. It features a dynamic architecture that monitors file systems or Kubernetes ConfigMaps to update MCP tools in re

This server falls under the APIs category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Automatically converts OpenAPI specifications into Model Con

Use Cases

Convert OpenAPI specs to MCP services dynamically
HTTP API exposure through Model Context Protocol
TaylorTrz

Maintainer

LicenseGPL-2.0
Languagephp
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-adapter

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Adapter

MCP Adapter is a TypeScript tool that automatically converts OpenAPI v2 and v3 specifications into Model Context Protocol applications, enabling any HTTP REST API to be consumed by MCP-compatible AI clients without manual tool definitions. It features a dynamic architecture that watches file system paths or Kubernetes ConfigMaps for OpenAPI spec changes and live-reloads the generated MCP tools without restarting the server. Developers use it to rapidly expose internal APIs, third-party services, or legacy REST endpoints as MCP tools that Claude and other LLMs can call directly.

Prerequisites

  • Python 3.11 or 3.12 recommended (project targets 3.14 but broader compatibility is advised)
  • Node.js and npm installed for running the npx entry point
  • An OpenAPI v2 or v3 specification file for the API you want to expose
  • An MCP-compatible client such as Claude Desktop
  • Optional: a Kubernetes cluster with ConfigMap support for production deployments
1

Clone the repository

Clone the mcp-adapter repository and navigate into the project directory.

git clone https://github.com/TaylorTrz/mcp-adapter.git
cd mcp-adapter
2

Install Python dependencies

Install the required Python packages. Use Python 3.11 or 3.12 for the broadest compatibility with the dependency set.

pip install -r requirements.txt
3

Prepare your OpenAPI specification

Place your OpenAPI v2 or v3 spec file (JSON or YAML) in the project directory or a path the adapter can watch. The adapter will parse it and generate MCP tools for each operation defined in the spec.

4

Start the MCP adapter server

Run the adapter, pointing it at your OpenAPI spec file. The server will expose the converted tools over the MCP protocol and begin watching the spec file for changes.

npx mcp-adapter --spec ./your-api-spec.yaml
5

Configure your MCP client

Register the adapter as an MCP server in your Claude Desktop configuration so the AI can discover and call the generated API tools.

{
  "mcpServers": {
    "mcp-adapter": {
      "command": "npx",
      "args": ["mcp-adapter", "--spec", "/absolute/path/to/openapi.yaml"]
    }
  }
}
6

Verify tool discovery

In your MCP client, ask the AI to list available tools. You should see one tool per API operation defined in your OpenAPI spec, named according to the operation IDs in the specification.

MCP Adapter Examples

Client configuration

Claude Desktop configuration to launch mcp-adapter with a local OpenAPI spec file.

{
  "mcpServers": {
    "mcp-adapter": {
      "command": "npx",
      "args": ["mcp-adapter", "--spec", "/path/to/openapi.yaml"]
    }
  }
}

Prompts to try

Example prompts that exercise API tools automatically generated from an OpenAPI specification.

- "List all the API tools you have available from the adapter"
- "Call the createUser operation with name 'Alice' and email '[email protected]'"
- "Use the listProducts tool to fetch the first page of products from the API"
- "What parameters does the updateOrder tool require?"
- "Search for available API operations related to payments"

Troubleshooting MCP Adapter

The adapter fails to parse the OpenAPI spec or reports schema errors

Validate your spec against the OpenAPI 3.0 or Swagger 2.0 schema using a tool like Swagger Editor (editor.swagger.io) before passing it to the adapter. Ensure the file path is absolute and the file is readable by the process.

Python version compatibility errors during startup

The project targets Python 3.14 but this version has limited library support. Switch to Python 3.11 or 3.12 using pyenv or a virtual environment ('python3.11 -m venv venv && source venv/bin/activate') and reinstall dependencies.

Tool changes in the OpenAPI spec are not reflected in the MCP client

The adapter watches the spec file for changes and reloads tools dynamically, but the MCP client may cache the tool list. Restart your MCP client or disconnect and reconnect to the server to force a fresh tool discovery handshake.

Frequently Asked Questions about MCP Adapter

What is MCP Adapter?

MCP Adapter is a Model Context Protocol (MCP) server that automatically converts openapi specifications into model context protocol applications, enabling http apis to be managed as mcp services. it features a dynamic architecture that monitors file systems or kubernetes configmaps to update mcp tools in re It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Adapter?

Follow the installation instructions on the MCP Adapter GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Adapter?

MCP Adapter works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Adapter free to use?

Yes, MCP Adapter is open source and available under the GPL-2.0 license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-adapter": { "command": "npx", "args": ["-y", "mcp-adapter"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use MCP Adapter?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides