MCP cover image
See in Github
2025-04-14

A zap to build MCP Servers

0

Github Watches

0

Github Forks

0

Github Stars

ZapToMCP

Valkeyrie

⚠️ Work in Progress

Warning: This repository is currently under active development. The API and implementation details are subject to change. Use at your own risk.

GitHub package.json version node:20 pnpm@10.8.1 npm License: MIT TypeScript Biome

ZapToMCP is a monorepo containing tools and libraries for building Model Context Protocol (MCP) servers and clients. It provides a streamlined way to create, deploy, and manage MCP-compatible services.

Overview

The Model Context Protocol (MCP) is an open standard for communication between AI assistants and tools. ZapToMCP simplifies the process of building MCP-compatible servers and clients, allowing developers to focus on creating powerful AI experiences rather than implementing protocol details.

Repository Structure

This monorepo contains the following packages:

  • @zaptomcp/sdk : A TypeScript implementation of the Model Context Protocol
  • @zaptomcp/server : A higher-level abstraction for creating MCP servers
  • More packages coming soon...

Getting Started

Prerequisites

  • Node.js >= 20
  • pnpm >= 10.8.1

Installation

Clone the repository:

git clone https://github.com/hoghweed/zaptomcp.git
cd zaptomcp

Install dependencies:

pnpm install

Installation

# Install dependencies
pnpm install

# Bootstrap the monorepo
pnpm bootstrap

Development

Available Scripts

  • pnpm dev: Start development mode for all packages
  • pnpm build: Build all packages
  • pnpm clean: Clean build artifacts
  • pnpm lint: Run linting across all packages
  • pnpm format: Format code across all packages
  • pnpm typecheck: Run type checking across all packages
  • pnpm commit: Create a commit using conventional commit format

Code Quality

This project uses:

  • Biome for linting and formatting
  • TypeScript for type checking
  • Husky for git hooks
  • Commitlint for commit message validation

@zaptomcp/sdk

The SDK package provides a TypeScript implementation for interacting with the Model Context Protocol (MCP).

Features

  • Multiple transport implementations:
    • In-memory
    • SSE (Server-Sent Events)
    • Stdio
    • Streamable HTTP
  • Type-safe API
  • Built with Fastify for high performance
  • Support for both ESM and CommonJS

Installation

pnpm add @zaptomcp/sdk

Usage

Usage Creating an MCP Server

import { McpServer } from '@zaptomcp/sdk';

// Create a server with basic information
const server = new McpServer(
  {
    name: "my-mcp-server",
    version: "1.0.0"
  },
  {
    capabilities: {
      // Define your server capabilities
      sampling: {},
      prompts: {},
      resources: {},
      tools: {},
      logging: {}
    },
    instructions: "This is an MCP-compatible server"
  }
);

// Connect the server to a transport
import { FastifyTransport } from '@zaptomcp/sdk/transports';
const transport = new FastifyTransport();
await server.connect(transport);

// Start listening for requests
await transport.listen(3000);
console.log("MCP server running on port 3000");

Creating an MCP Client

import { Client } from '@zaptomcp/sdk';

// Create a client with basic information
const client = new Client(
  {
    name: "my-mcp-client",
    version: "1.0.0"
  },
  {
    capabilities: {
      // Define your client capabilities
      sampling: {}
    }
  }
);

// Connect to an MCP server
import { HTTPClientTransport } from '@zaptomcp/sdk/transports';
const transport = new HTTPClientTransport('http://localhost:3000');
await client.connect(transport);

// Read a resource
const resource = await client.readResource({
  uri: "test://example/resource"
});

console.log(resource);

API Documentation

The SDK provides the following main exports:

  • Server: The main server class
  • transports: Various transport implementations
    • in-memory: In-memory transport
    • sse: Server-Sent Events transport
    • stdio: Standard I/O transport
    • streamable-http: HTTP transport with streaming support

Development

To work on the SDK:

# Navigate to the SDK package
cd packages/sdk

# Install dependencies
pnpm install

# Start development mode
pnpm dev

# Run tests
pnpm test

# Build the package
pnpm build

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch ( git checkout -b feature/amazing-feature )
  3. Commit your changes using conventional commits ( pnpm commit )
  4. Push to the branch ( git push origin feature/amazing-feature )
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

相关推荐

  • Aurity Ltd
  • Create and Publish Business Websites in seconds. AI will gather all the details about your website and generate link to your website.

  • John Rafferty
  • Text your favorite pet, after answering 10 questions about their everyday lives!

  • Carl Oscar Aaro
  • Structured recipes for food and desserts – ingredient lists and step-by-step recipe instructions from any input. Become surprised, try something new or breathe life into grandma's old recipe notebook.

  • Ian O'Connell
  • Provide players' names or enter Quickstart to start the game!

  • Convincible Ltd
  • You're in a stone cell – can you get out? A classic choose-your-adventure interactive fiction game, based on a meticulously-crafted playbook. With a medieval fantasy setting, infinite choices and outcomes, and dice!

  • analogchat.com
  • Efficient Spotify assistant for personalized music data.

  • Matthieu Savioux
  • Evaluates language quality of texts, responds with a numerical score between 50-150.

  • WangRongsheng
  • 🧑‍🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.

  • av
  • Effortlessly run LLM backends, APIs, frontends, and services with one command.

  • 1Panel-dev
  • 🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.

  • langgenius
  • Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

  • caio-moliveira
  • This project was created to demonstrate how we can connect with different Model Context Protocols (MCPs).

  • alibaba
  • an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

  • rulego
  • ⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.

  • Byaidu
  • PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/Zotero

    Reviews

    3 (2)
    Avatar
    user_jc21lJ7k
    2025-04-24

    I've been using zaptomcp for a while now, and it's been fantastic! Developed by hoghweed, this application truly stands out. The interface is intuitive, and the features are incredibly useful for managing my tasks efficiently. Highly recommended for anyone looking for a reliable MCP application.

    Avatar
    user_qxVkpwkB
    2025-04-24

    As a dedicated user of zaptomcp, I must say this tool by hoghweed has significantly streamlined my processes. Its intuitive design and robust functionality have made complex tasks much simpler. I highly recommend it to anyone looking for an efficient and reliable solution.