Name: 302AI BrowserUse
Author: 302ai

LABSCO SUMMARY

The browsing happens elsewhere and your side holds nothing but a task ID.

Submission and collection being separate calls is what keeps a long task from occupying the conversation while it runs. The task goes in as written — the tool is explicit that continuous, complex work does not need to be decomposed before it is handed over. Which model runs it is a property of the task rather than a server-wide setting, so two tasks in the same session can use different ones.

What it is

A two-call interface to 302AI's browser agent: submit a task, then fetch its result.

What you get

A browser task created from a plain description, on a model you name, without splitting the work into steps first.
A task ID returned immediately, and the result fetched against that ID once the run has produced one.

Requirements

A 302AI account and its key, supplied as 302AI_API_KEY.

Setup effort

One command plus a key — npx -y @302ai/browser-use-mcp, then supply credentials

See installation options

USE CASES

01

Handing off a multi-step web task and getting on with something else

The task is described once, in full, and the call returns immediately with the ID that identifies it.

createBrowserAgentTask

02

Picking up the result of a task submitted earlier

A run that has not finished yet returns nothing useful, so the ID has to survive until it does.

getBrowserAgentTaskResult

2 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`createBrowserAgentTask`

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.

BEFORE YOU INSTALL

What to know first

Tools you get

2 tools when we connected. createBrowserAgentTask submits a task and getBrowserAgentTaskResult polls for its result. The tool list is fetched from 302.AI's server at startup, so it can change without a package upgrade.

Requires

npx on PATH
302AI_API_KEY in your environment

Where it runs

All 3 documented clients run the server on your machine.

CONTEXT COST

Light Standing cost

Rated by the size of the 2 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

Server setup

TERMINAL

npx -y @302ai/browser-use-mcp

MCP Clients

Claude Desktop, ChatWise

JSON

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

Cherry Studio

CHERRY STUDIO · JSON

{
  "mcpServers": {
    "302ai-browser-use-mcp": {
      "name": "302ai-browser-use-mcp",
      "description": "",
      "isActive": true,
      "registryUrl": "",
      "command": "npx",
      "args": [
        "-y",
        "@302ai/browser-use-mcp"
      ],
      "env": {
        "302AI_API_KEY": "<YOUR_AI_API_KEY>"
      }
    }
  }
}

Cherry Studio uses the key as the server's id. The README's block uses the random id "Li2ZXXJkvhAALyKOFeO4N", which is also used in the blocks for other 302.AI servers, so two of them added together would overwrite each other. Here the key is the server's name. <YOUR_AI_API_KEY> is your 302.AI API key from dash.302.ai/apis/list.

302AI BrowserUse