AdsPower Browser Manager MCP server

Enables AI-driven browser profile management through AdsPower's local API, providing tools for creating, updating, opening, and deleting browsers with customizable fingerprints and proxy configurations.
Back to servers
Provider
AdsPower
Release date
Mar 28, 2025
Language
TypeScript
Stats
13 stars

AdsPower LocalAPI MCP Server is a Model Context Protocol server that enables large language models (LLMs) to interact with AdsPower browser's LocalAPI. This server allows you to create, manage, and automate browser instances with custom fingerprints directly through natural language commands to LLMs like Claude.

Installation Requirements

Before installing the MCP server, you need:

  • AdsPower browser installed
  • Node.js version 18 or greater

Setting Up the Server

For Claude Desktop

To integrate the server with Claude Desktop, you need to modify the Claude configuration file:

MacOS / Linux Configuration

Add the following to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "adspower-local-api": {
      "command": "npx",
      "args": ["-y", "local-api-mcp-typescript"]
    }
  }
}

Windows Configuration

Add the following to %APPDATA%/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "adspower-local-api": {
      "command": "cmd",
      "args": ["/c", "npx", "-y", "local-api-mcp-typescript"]
    }
  }
}

Using the MCP Server

After installation, you can interact with the AdsPower browser through natural language commands in Claude. Here are some examples of what you can do:

Managing Browsers

You can use natural language to:

  • Create browsers with specific configurations
  • Open existing browsers
  • Close browsers
  • Update browser settings
  • Delete browsers

Example Commands

You can tell Claude:

  • "Create an Android UA browser using Chrome 134"
  • "Help me with random UA, random fingerprint, random cookie generation, create 3 browsers, use 134 cores, and open them"

Available Tools

Browser Management

  • open_browser: Opens a browser instance

    • Parameters: serialNumber (optional), userId (optional)
  • close_browser: Closes a browser instance

    • Parameters: userId (required)
  • create_browser: Creates a new browser with custom settings

    • Key parameters:
      • groupId: The group ID for the browser
      • name: Browser name (optional)
      • system: System type (optional)
      • openUrls: URLs to open (optional)
      • userProxyConfig: Proxy configuration
      • fingerprintConfig: Browser fingerprint configuration (optional)
  • update_browser: Updates an existing browser's settings

    • Parameters: Similar to create_browser, plus userId to identify the browser
  • delete_browser: Deletes browser instances

    • Parameters: userIds (array of browser IDs to delete)

Browser Listing and Organization

  • get_browser_list: Retrieves a list of browsers

    • Parameters: groupId (optional), size (optional), id (optional), etc.
  • get-opened_browser: Gets a list of currently opened browsers

  • move_browser: Moves browsers between groups

    • Parameters: groupId (target group), userIds (browsers to move)

Group Management

  • create_group: Creates a new browser group

    • Parameters: groupName, remark (optional)
  • update_group: Updates a group's settings

    • Parameters: groupId, groupName, remark (optional)
  • get_group_list: Gets a list of browser groups

    • Parameters: name (optional), size (optional)
  • get-application_list: Gets a list of applications

    • Parameters: size (optional)

Advanced Configuration

Proxy Configuration

When creating or updating a browser, you can specify proxy settings using the userProxyConfig object:

{
  "proxy_soft": "brightdata",
  "proxy_type": "http",
  "proxy_host": "example.com",
  "proxy_port": "8080",
  "proxy_user": "username",
  "proxy_password": "password"
}

Fingerprint Configuration

You can customize browser fingerprints with the fingerprintConfig object:

{
  "automatic_timezone": "1",
  "timezone": "America/New_York",
  "language": ["en-US", "en"],
  "browser_kernel_config": {
    "version": "134",
    "type": "chrome"
  },
  "random_ua": {
    "ua_version": ["134"],
    "ua_system_version": ["windows"]
  }
}

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later