Vercel AI MCP server

The AI MCP Server is an implementation that supports OpenAI and Mistral models using the Vercel AI SDK. This server allows you to access powerful language models through a standardized Model Context Protocol interface, making it easier to build AI-powered applications.

Supported Providers

OpenAI

• Models: gpt-4-turbo, gpt-4, gpt-3.5-turbo
• Features: Structured output, system prompts

Mistral

• Models: mistral-large-latest, mistral-small-latest, pixtral-large-latest
• Features: Safe prompts, system prompts

Prerequisites

Before installing the MCP server, ensure you have:

• Node.js 18 or higher
• OpenAI API key (for OpenAI features)
• Mistral API key (for Mistral features)

Installation

1. Clone the repository:

git clone https://github.com/yourusername/openai-mcp-server.git
cd openai-mcp-server

2. Install dependencies:

npm install

3. Set up environment variables:

   Create a .env file in the root directory with the following variables:

OPENAI_API_KEY=your_openai_api_key_here
MISTRAL_API_KEY=your_mistral_api_key_here
PORT=3000  # Optional, defaults to 3000

4. Start the server:

npm start

Usage

Basic Usage

Once the server is running, it will be available at http://localhost:3000 (or the port you specified).

You can send requests to the server using any MCP-compatible client. The server exposes endpoints for both OpenAI and Mistral models.

API Endpoints

The MCP server provides the following endpoints:

• /v1/mcp - The main MCP endpoint for all model interactions

Example Request

Here's an example of how to make a request to the server:

const response = await fetch('http://localhost:3000/v1/mcp', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4-turbo',  // or 'mistral-large-latest'
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello, how are you?' }
    ],
    stream: true,  // Optional, for streaming responses
    temperature: 0.7  // Optional, controls randomness
  })
});

Configuration Options

The server accepts the following configuration options in your request:

• model: The model to use (e.g., 'gpt-4-turbo', 'mistral-large-latest')
• messages: Array of message objects with 'role' and 'content'
• stream: Boolean indicating whether to stream the response
• temperature: Controls randomness (0-1)
• max_tokens: Maximum number of tokens to generate
• tools: Array of tool definitions for function calling (OpenAI only)

Troubleshooting

Common Issues

• Authentication Errors: Ensure your API keys are correctly set in the .env file
• Connection Refused: Check that the server is running and the port is not blocked
• Model Not Found: Verify that you're using a supported model name

If you encounter issues, check the server logs for more detailed error information.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "vercel-ai" '{"command":"npx","args":["-y","mcp-vercel-ai"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

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

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

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect