Zntl MCP Server

🚀 MCP Server for Transcripter Project

This is a Model Context Protocol (MCP) server implemented for the Transcripter project. This package provides tools and resources for AI-driven functions using the MCP standard.

🚀 Quick Start

This MCP server offers a standardized interface for interacting with AI models, enabling users to perform tasks such as testing API endpoints, searching transcriptions, and generating summaries.

✨ Features

Tools

• test-api: Test API endpoints and return results.
• transcription-search: Search transcription content with filtering and pagination.
• transcription-summary: Generate summaries of transcription content using AI.

Resources

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

📦 Installation

Ensure you have the following installed:

• Node.js >= 18.0.0
• npm >= 7.0.0

npm install

🛠️ Build

# Build for both ESM and CommonJS
npm run build

# Build only for ESM
npm run build:esm

# Build only for CommonJS
npm run build:cjs

▶️ Run

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

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

🧪 Test

npm test

💻 Usage Examples

Basic Usage

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);
}

Advanced Usage

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);
}

🤝 Integration with Transcripter

This MCP server integrates with the Transcripter project, providing AI-driven functions for transcription and analysis. It serves as a standardized interface for AI model interactions.

📁 Project Structure

📄 License

MIT