MCP.so
ログイン

302_browser_use_mcp

@302ai

302_browser_use_mcp について

Automatically create a remote browser to complete your specified tasks, developed based on Browser Use + Sandbox.

基本情報

カテゴリ

ブラウザ自動化

トランスポート

stdio

公開者

302ai

投稿者

Jomy Wu

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": {
    "302ai-browser-use-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@302ai/browser-use-mcp"
      ],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

ツール

2

Create a browser agent task, and return the task id. This agent can handle continuous complex tasks, and you do not need to break down the tasks. Just input them directly. Clearly return the task_id to the user for use in the next request.

Get the result of the browser agent task. If no results are obtained, clearly return the task_id to the user for use in the next request.

概要

What is 302_browser_use_mcp?

302_browser_use_mcp is an AI-powered browser automation server that implements the Model Context Protocol (MCP) for natural language browser control and web research.

How to use 302_browser_use_mcp?

Add the server configuration to your MCP client (e.g., Claude Desktop, Cherry Studio, or ChatWise) using the npx command with the @302ai/browser-use-mcp package and set your 302AI_API_KEY environment variable. You can run it locally in stdin mode or host it as a remote HTTP server.

Key features of 302_browser_use_mcp

  • Dynamic loading of tool list from remote server.
  • Supports both local stdin and remote HTTP server modes.
  • Provides tools for creating and querying browser automation tasks.
  • Easy integration with Claude Desktop, Cherry Studio, and ChatWise.
  • Debuggable via the MCP Inspector.

Use cases of 302_browser_use_mcp

  • Automate web research through natural language instructions.
  • Control a browser remotely using an AI assistant.
  • Integrate browser actions into AI-powered workflows.

FAQ from 302_browser_use_mcp

What tools does 302_browser_use_mcp provide?

The server exposes two tools: Create Browser Automation Task and Query Browser Task Status. Details are available in the linked API documentation.

What are the runtime dependencies?

The server is distributed as an npm package (@302ai/browser-use-mcp). It can be invoked directly via npx without explicit installation, but local development requires Node.js and npm install.

How do I authenticate with the server?

You must provide a valid 302AI_API_KEY in the environment configuration. You can obtain one from the 302.AI dashboard at https://dash.302.ai/apis/list.

What transport modes are supported?

Two modes are supported: local stdin (default when used with MCP clients) and a remote HTTP server mode for hosting elsewhere.

Is 302_browser_use_mcp open source?

The README does not explicitly state the license, but it is part of the 302.AI open-source ecosystem and the code is available via npm for modification.

コメント

「ブラウザ自動化」の他のコンテンツ