MCP ExplorerExplorer

Mcp Client Browser

@autoexpecton a year ago
4 MIT
FreeCommunity
AI Systems
TypeScript SDK for using large language models with an MCP server directly in the browser, powered by Cherry Studio's prompt templates.

Overview

What is Mcp Client Browser

mcp-client-browser is a TypeScript SDK designed for direct interaction with large language models via an MCP server in the browser, utilizing Cherry Studio’s prompt templates.

Use cases

Use cases include AI chatbots powered by LLMs in the browser, embedding customizable prompt workflows into frontend applications, and creating interactive educational or creative writing tools.

How to use

To use mcp-client-browser, ensure your MCP server supports CORS and the Cherry prompt specification. Installation instructions will be provided soon, followed by usage guidelines.

Key features

Key features include running entirely in the browser without backend requirements, seamless communication with MCP-compatible servers, built-in support for Cherry Studio’s prompt format, a simple and extendable TypeScript-friendly API, and easy integration into modern web applications.

Where to use

mcp-client-browser is suitable for web applications that require interaction with large language models, particularly in educational, creative, or chatbot scenarios.

Content

MCP-CLIENT-BROSWER

mcp-client-browser is a TypeScript library that brings MCP (Model Control Protocol) support to the browser. It enables seamless interaction with large language models (LLMs) through an MCP server, leveraging Cherry Studio’s prompt templates and communication logic.

✨ Features

  • 🌐 Runs entirely in the browser (no backend required)
  • ⚡ Communicates with MCP-compatible servers
  • 🧠 Built-in support for Cherry Studio’s MCP prompt format
  • 🛠️ Simple, extendable, and TypeScript-friendly API
  • 📦 Designed for easy integration into modern web apps

🚀 Getting Started

Installation

npm i @autoexpect/mcp-sseclient-browser

Usage

let mcpClient = new MCPClient(
  [
    {
      url: new URL('/api/mcps/sse', window.location.origin)
    }
  ],
  {
    baseUrl: window.location.origin + "/v1",
    apiKey: "sk-default",
    model: "deepseek-v3",
  }
);
await mcpClient.connect();
await mcpClient.processQueryStream(
  "System Prompt",
  "User Prompt",
  true,
  (chunk) => {
  },
  (fullResponse) => {
  }
);

✅ Make sure your MCP server supports CORS and the Cherry prompt specification.

💡 Use Cases

  • AI chatbots powered by LLMs directly in the browser
  • Embedding customizable prompt workflows into frontend apps
  • Creating interactive educational or creative writing tools

🧩 Integrations

  • Cherry Studio: Easily plug in Cherry-style prompt templates
  • Compatible with most OpenAI-compatible or custom MCP servers

🛡️ Security & Privacy

This library does not store user data. All interactions happen directly between the browser and the configured MCP server.

📄 License

MIT License

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers