Skip to main content
Glama
302ai

302AI BrowserUse MCP Server

Official
by 302ai
README.md
# <p align="center">πŸ€– 302AI BrowserUse MCP ServerπŸš€βœ¨</p>

<p align="center">An AI-powered browser automation server implementing Model Context Protocol (MCP) for natural language browser control and web research.</p>

<a href="https://glama.ai/mcp/servers/@302ai/302_browser_use_mcp">
  <img width="380" height="200" src="https://glama.ai/mcp/servers/@302ai/302_browser_use_mcp/badge" alt="302AI BrowserUse Server MCP server" />
</a>

<p align="center"><a href="https://www.npmjs.com/package/@302ai/browser-use-mcp" target="blank"><img src="https://file.302.ai/gpt/imgs/github/20250102/72a57c4263944b73bf521830878ae39a.png" /></a></p >

<p align="center"><a href="README_zh.md">δΈ­ζ–‡</a> | <a href="README.md">English</a> | <a href="README_ja.md">ζ—₯本θͺž</a></p>

![](docs/302_browser_use_mcp_en.png) 

## Previews

Here are some usage examples
![](docs/302_browser_use_mcp_en_screenshot_01.jpg)      

Here is the list of supported tools
![](docs/302_browser_use_mcp_en_screenshot_02.png)


## ✨ Features ✨

- πŸ”§ Dynamic Loading - Automatically update tool list from remote server.
- 🌐 Multi modes supported, you can use `stdin` mode locally, or host it as a remote HTTP server

## πŸš€ Tool List
- [Create Browser Automation Task](https://302ai-en.apifox.cn/api-282235063)
- [Query Browser Task Status](https://302ai-en.apifox.cn/api-282235713)


## Development

Install dependencies:

```bash
npm install
```

Build the server:

```bash
npm run build
```

For development with auto-rebuild:

```bash
npm run watch
```

## Installation

To use with Claude Desktop, add the server config:

On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`    
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`

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

To use with Cherry Studio, add the server config:

```json
{
  "mcpServers": {
    "Li2ZXXJkvhAALyKOFeO4N": {
      "name": "302ai-browser-use-mcp",
      "description": "",
      "isActive": true,
      "registryUrl": "",
      "command": "npx",
      "args": [
        "-y",
        "@302ai/browser-use-mcp"
      ],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
```

To use with ChatWise, copy the following content to clipboard
```json
{
  "mcpServers": {
    "302ai-sandbox-mcp": {
      "command": "npx",
      "args": ["-y", "@302ai/browser-use-mcp"],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
```
Go to Settings -> Tools -> Add button -> Select Import from Clipboard
![](docs/302_browser_use_mcp_en_screenshot_03.png)

### Find Your 302AI_API_KEY [here](https://dash.302.ai/apis/list)
[Using Tutorials](https://help.302.ai/en/docs/API-guan-li)

### Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:

```bash
npm run inspector
```

The Inspector will provide a URL to access debugging tools in your browser.

## ✨ About 302.AI ✨
[302.AI](https://302.ai/en/) is an enterprise-oriented AI application platform that offers pay-as-you-go services, ready-to-use solutions, and an open-source ecosystem.✨
1. 🧠 Integrates the latest and most comprehensive AI capabilities and brands, including but not limited to language models, image models, voice models, and video models.
2. πŸš€ Develops deep applications based on foundation models - we develop real AI products, not just simple chatbots
3. πŸ’° Zero monthly fee, all features are pay-per-use, fully open, achieving truly low barriers with high potential.
4. πŸ›  Powerful management backend for teams and SMEs - one person manages, many people use.
5. πŸ”— All AI capabilities provide API access, all tools are open source and customizable (in progress).
6. πŸ’‘ Strong development team, launching 2-3 new applications weekly, products updated daily. Developers interested in joining are welcome to contact us.

TDQS

A3.8/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one creates a task, the other retrieves its result. There is no overlap or ambiguity.

Naming Consistency4/5

Both tools use camelCase and follow a verb_noun pattern, but one ends with 'Task' and the other with 'TaskResult', introducing minor inconsistency. Still understandable.

Tool Count3/5

With only 2 tools, the server feels minimal. While it may suffice for the specific purpose of managing browser agent tasks, it is on the low end of reasonable scope.

Completeness2/5

The tool set covers creation and result retrieval, but lacks any management operations (e.g., list, cancel, retry). This limits the agent's ability to handle errors or task lifecycles.

Maintenance

ActivityInactive
ResponsivenessNo issues