MCPify (OpenAPI) MCP server

This server implements the Model Context Protocol (MCP), allowing you to transform OpenAPI specifications into MCP tools, which can enhance the interaction between applications and large language models.

Installation

To install MCPify, use npm:

npm install @mcpify/core

You can also use yarn:

yarn add @mcpify/core

Or with pnpm:

pnpm add @mcpify/core

Usage

Basic Setup

Import and initialize the MCPify core module in your application:

import { MCPify } from '@mcpify/core';

// Initialize with your OpenAPI specification
const mcpTool = new MCPify({
  openApiSpec: './path/to/your/openapi.yaml'
});

Converting OpenAPI to MCP Tool

Transform your API specification into an MCP-compatible tool:

// Convert the OpenAPI spec to MCP format
const mcpTool = await mcpify.convert();

// The resulting tool can be used with MCP-compatible LLMs
console.log(mcpTool);

Configuration Options

You can customize the conversion process with various options:

const mcpTool = new MCPify({
  openApiSpec: './path/to/your/openapi.yaml',
  options: {
    includeAuth: true,
    summarizeEndpoints: true,
    verbose: false
  }
});

Integrating with LLM Applications

After creating your MCP tool, you can integrate it with applications that support the Model Context Protocol:

// Example integration with an LLM framework
import { LlmFramework } from 'llm-framework';

const llm = new LlmFramework();
llm.registerTool(mcpTool);

const response = await llm.process("Please find information about...");

Troubleshooting

Common Issues

• Specification Not Found: Ensure the path to your OpenAPI specification is correct
• Parsing Errors: Verify your OpenAPI specification is valid and follows the OpenAPI standard
• Authorization Issues: Check that any required authentication details are properly configured

If you encounter problems, enable verbose mode for more detailed logs:

const mcpTool = new MCPify({
  openApiSpec: './path/to/your/openapi.yaml',
  options: {
    verbose: true
  }
});

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

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

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.