MCP CLIENT BROSWER

@autoexpect

代码仓库

基本信息

分类

浏览器自动化

许可证

MIT

传输方式

stdio

作者

autoexpect

关于 MCP CLIENT BROSWER

TypeScript SDK for using large language models with an MCP server directly in the browser, powered by Cherry Studio's prompt templates.

MCP CLIENT BROSWER 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

MCP CLIENT BROSWER 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP-CLIENT-BROSWER?

MCP-CLIENT-BROSWER is a TypeScript library that brings MCP (Model Control Protocol) support to the browser, enabling interaction with large language models (LLMs) through an MCP server. It leverages Cherry Studio's prompt templates and communication logic and is designed for use in modern web applications.

How to use MCP-CLIENT-BROSWER?

Install via npm i @autoexpect/mcp-sseclient-browser. Instantiate the MCPClient class with an array of server configurations and an options object (containing base URL, API key, and model), then call connect() and processQueryStream() with system and user prompts, a boolean flag, and callback functions for chunks and the full response.

Key features of MCP-CLIENT-BROSWER

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

Use cases of MCP-CLIENT-BROSWER

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

常见问题

How does MCP-CLIENT-BROSWER run without a backend?

It operates entirely in the browser, communicating directly with MCP-compatible servers via SSE (Server-Sent Events) as shown in the configuration example.

Does MCP-CLIENT-BROSWER store any user data?

No. The library does not store user data; all interactions happen directly between the browser and the configured MCP server.

What dependencies or runtime requirements does it have?

The MCP server must support CORS and the Cherry prompt specification. The library is TypeScript-based and works with OpenAI-compatible or custom MCP servers.