WeChat MiniProgram MCP server

This MCP server implementation enables real-time communication with models through the Model Context Protocol (MCP). It provides a standardized way to interact with language models and retrieve context information about model responses.

Installation

You can install the minium-mcp-server using npm:

npm install minium-mcp-server

For development or to run it directly from the source, clone the repository and install dependencies:

git clone https://github.com/your-username/minium-mcp-server.git
cd minium-mcp-server
npm install

Usage

Running the MCP Server

To start the MCP server, use the following command:

npx @modelcontextprotocol/inspector uv --directory /path/to/minium-mcp-server/sse run minium-mcp-server

Replace /path/to/minium-mcp-server/sse with the actual path to your server's SSE (Server-Sent Events) directory.

Inspecting MCP Responses

The MCP server works with the Model Context Protocol Inspector, which allows you to visualize and debug model responses and their associated context information.

To use the inspector with your MCP server:

1. Start your MCP server as shown above
2. Open the inspector in your browser (typically available at http://localhost:3000)
3. Connect to your running MCP server instance

Example API Interactions

You can interact with the MCP server using standard HTTP requests:

// Example of sending a prompt to the MCP server
const response = await fetch('http://localhost:3000/generate', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    prompt: "Explain the concept of recursion",
    options: {
      max_tokens: 150
    }
  })
});

const result = await response.json();
console.log(result);

Configuration Options

Server Configuration

You can configure the MCP server by modifying the settings in your configuration file or environment variables:

• PORT: The port number on which the server runs (default: 3000)
• MODEL_PROVIDER: Specify which model provider to use
• API_KEY: Your API key for the model provider

Model Parameters

When making requests to the server, you can specify various parameters:

• max_tokens: Maximum number of tokens to generate
• temperature: Controls randomness (0.0-1.0)
• top_p: Controls diversity via nucleus sampling
• frequency_penalty: Reduces repetition of token sequences
• presence_penalty: Reduces repetition of topics

Troubleshooting

If you encounter issues:

1. Verify your API keys are correctly configured
2. Check server logs for error messages
3. Ensure your network allows connections to the server
4. Confirm you're using the correct endpoint URLs

For more detailed troubleshooting information, check the server logs which are output to the console when running the server.

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.