InBrowserMCP Project MCP Server

@LofiSu

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

LofiSu

关于 InBrowserMCP Project MCP Server

express框架搭建的mcp-sdk实例

InBrowserMCP Project MCP Server 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

InBrowserMCP Project MCP Server 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 InBrowserMCP Project?

The InBrowserMCP Project implements a system based on the Model Context Protocol (MCP) that allows an AI model to interact with a web browser via a browser extension. It consists of a React frontend, a Node.js MCP server, and a Chrome browser extension that communicate to execute browser actions.

How to use InBrowserMCP Project?

Start the MCP server (cd mcp-server && pnpm dev), load the Browser Extension in Chrome (chrome://extensions/), start the Frontend (cd frontend && pnpm dev), then open the frontend application at http://localhost:5173 to send commands that control the browser.

Key features of InBrowserMCP Project

React-based frontend for user interaction with AI
Node.js MCP server implementing the MCP specification
Chrome browser extension connects via WebSocket
Server-Sent Events (SSE) for streaming responses
Orchestrates browser navigation, clicks, typing, and content extraction

Use cases of InBrowserMCP Project

AI-controlled web browsing for automation
Automated form filling and data scraping via browser
Testing web pages with AI-driven navigation
Building AI assistants that can interact with live websites

常见问题

What components make up the InBrowserMCP Project?

The project has three main parts: a React frontend (port 5173), a Node.js MCP server (port 3000), and a Chrome browser extension (WebSocket port 8081).

How does the architecture work?

The frontend sends user commands to the MCP server, which translates them into MCP tool calls. The server sends browser actions to the extension via WebSocket, and the extension executes them and returns results. The server then streams responses back to the frontend via SSE.

Does the project include an AI model?

No, an AI model is not explicitly implemented in this project; it is assumed that the frontend or MCP server will interact with an external AI model as part of the system.

What are the runtime requirements for running InBrowserMCP Project?

You need Node.js and pnpm for the server and frontend, and Google Chrome to load the browser extension. All communication uses localhost ports 5173, 3000, and 8081.

How do I start using InBrowserMCP Project?

Follow the general workflow: start the MCP server, load the extension in Chrome, start the frontend, and open the frontend URL. Detailed instructions are in the respective README files for each component.

开发工具分类下的更多 MCP 服务器

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

ShipMyForm

ShipMyForm.com

Form backend for static sites. Create form endpoints, get paste-ready markup for HTML, React, Vue, Svelte and Astro, and read submission stats — straight from your agent. Submissions are spam-filtered, stored, and routed