Transcripter MCP server

This MCP server implementation for the Transcripter project provides tools and resources for AI-powered features using the Model Context Protocol standard, enabling transcription searching, summarization, and API testing capabilities.

Requirements

• Node.js >= 18.0.0
• npm >= 7.0.0

Installation

Installation is simple and requires just one command:

npm install

Running the Server

Start the MCP server with these commands:

# Start the MCP server on the default port (3500)
npm run server

# Start the MCP server on a custom port
npm run server 4000

Available Tools and Resources

Tools

The server provides several AI-powered tools:

• test-api: Test API endpoints and return the results
• transcription-search: Search transcriptions with filtering and pagination
• transcription-summary: Generate a summary of a transcription using AI

Resources

Access to key data resources:

• transcription://{id}: Access transcription data by ID
• analysis://{id}: Access analysis data by ID

Usage Examples

Using the test-api Tool

This example demonstrates how to connect to the MCP server and test an API endpoint:

import { Client } from "@modelcontextprotocol/sdk/client";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse";

async function testApiEndpoint() {
  // Connect to the MCP server
  const transport = new SSEClientTransport("http://localhost:3500/sse", "http://localhost:3500/message");
  const client = new Client();
  await client.connect(transport);
  
  // Use the test-api tool
  const result = await client.tools.execute("test-api", {
    endpoint: "transcriptions",
    method: "GET",
  });
  
  console.log(result);
}

Accessing Transcription Resources

This example shows how to retrieve a transcription resource by ID:

import { Client } from "@modelcontextprotocol/sdk/client";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse";

async function getTranscription(id: number) {
  // Connect to the MCP server
  const transport = new SSEClientTransport("http://localhost:3500/sse", "http://localhost:3500/message");
  const client = new Client();
  await client.connect(transport);
  
  // Access the transcription resource
  const transcription = await client.resources.get(`transcription://${id}`);
  
  console.log(transcription);
}

Creating a Transcription Summary

To generate an AI-powered summary of a transcription:

import { Client } from "@modelcontextprotocol/sdk/client";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse";

async function summarizeTranscription(id: number) {
  const transport = new SSEClientTransport("http://localhost:3500/sse", "http://localhost:3500/message");
  const client = new Client();
  await client.connect(transport);
  
  // Generate a summary using the transcription-summary tool
  const summary = await client.tools.execute("transcription-summary", {
    transcriptionId: id,
    maxLength: 500  // Optional: specify maximum summary length
  });
  
  console.log(summary);
}

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.