MCP Starter Project

Name: MCP Starter Project
Author: sharmatriloknath

@sharmatriloknath

リポジトリ

MCP Starter Project について

How to setup mcp server and mcp client.

#mcp #mcp-server #mcp-client

基本情報

カテゴリ

開発者ツール

ランタイム

node

トランスポート

stdio

公開者

sharmatriloknath

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp_starter": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Starter Project?

MCP Starter Project is a template for building AI applications with the Model Context Protocol (MCP). It includes a Python server that defines documentation search tools and a TypeScript client that connects to the server and integrates with HuggingFace models. It is designed for developers who want to learn or quickly prototype MCP‑based AI assistants.

How to use MCP Starter Project?

Set up the Python server by creating a virtual environment, installing dependencies, adding a .env file with SERPER_API_KEY, and running python main.py. For the client, install Node.js dependencies, add a .env with HUGGINGFACE_API_KEY, build the TypeScript code, then start it with node build/index.js ../mcp-server/main.py. Use the POST /chat endpoint with a JSON body containing query and sessionId to interact with the system.

Key features of MCP Starter Project

Documentation search tool for LangChain, LlamaIndex, and OpenAI
Session‑based conversation history management
Seamless integration of HuggingFace models with tool calls
Two HTTP endpoints: health check and chat
Robust error handling for API and tool execution

Use cases of MCP Starter Project

Building a documentation‑focused chatbot for popular AI libraries
Prototyping an MCP‑based conversational AI assistant
Learning how to implement MCP servers and clients
Creating a search‑enhanced help desk for developer documentation

FAQ from MCP Starter Project

What are the prerequisites for MCP Starter Project?

You need Python 3.11+, Node.js 18+, a HuggingFace API key, and a Serper API key.

How do I configure environment variables?

Place your Serper API key in mcp-server/.env as SERPER_API_KEY and your HuggingFace API key in mcp-clients/.env as HUGGINGFACE_API_KEY.

What tools does the MCP server expose?

The server exposes a documentation search tool that can query LangChain, LlamaIndex, and OpenAI documentation.

How do I start the application?

First run python main.py from the mcp-server directory, then in another terminal run node build/index.js ../mcp-server/main.py from the mcp-clients directory.

What API endpoints are available?

The client serves GET /health for health checks and POST /chat for sending queries. The chat endpoint expects a JSON body with query and sessionId fields.