Question 1

What is the browser-use MCP Server?

Accepted Answer

The browser-use MCP Server is an AI-driven browser automation server that implements the Model Context Protocol (MCP) for natural language browser control and web research. It allows AI models to interact with web browsers using natural language commands.

Question 2

What is MCP?

Accepted Answer

MCP stands for Model Context Protocol. It is an open protocol that standardizes how applications provide context to Large Language Models (LLMs).

Question 3

What are the key features of the browser-use MCP Server?

Accepted Answer

Key features include MCP integration, browser automation, visual understanding (screenshot analysis), state persistence, multi-LLM support, a deep research tool, environment variable configuration, and CDP connection.

Question 4

Which LLM providers are supported?

Accepted Answer

The server supports OpenAI, Anthropic, Azure, DeepSeek, Google, Mistral, Ollama, OpenRouter, Alibaba, Moonshot, and Unbound AI.

Question 5

What is the `run_browser_agent` tool?

Accepted Answer

The `run_browser_agent` tool executes a browser automation task based on natural language instructions and waits for it to complete.

Question 6

What is the `run_deep_search` tool?

Accepted Answer

The `run_deep_search` tool performs in-depth web research on a topic, generates a report, and waits for completion.

Question 7

How do I configure the server?

Accepted Answer

The server is configured using environment variables. You can set these in your system or place them in a `.env` file in the project root.

Question 8

What is CDP and how do I connect to my own browser?

Accepted Answer

CDP stands for Chrome DevTools Protocol. You can connect to your own Chrome/Chromium browser by launching it with remote debugging enabled and setting the `MCP_USE_OWN_BROWSER` and `CHROME_CDP` environment variables.

Question 9

What if I get API errors?

Accepted Answer

Double-check that the correct API key environment variable is set for your chosen `MCP_MODEL_PROVIDER`, or that `MCP_API_KEY` is set. Verify keys and endpoints (`AZURE_OPENAI_ENDPOINT` is required for Azure).

Question 10

How do I troubleshoot browser conflicts?

Accepted Answer

If *not* using `CHROME_CDP` (`MCP_USE_OWN_BROWSER=false`), ensure no other conflicting Chrome instances are running with the same user data directory if `CHROME_USER_DATA` is specified.

Question 11

How does this integrate with UBOS?

Accepted Answer

The browser-use MCP Server integrates with UBOS by allowing you to create AI Agents within the UBOS platform that utilize the server to interact with web browsers. You can then orchestrate these agents within UBOS workflows.

Question 12

What are the prerequisites for running the server?

Accepted Answer

You need Python 3.11 or higher, `uv` (fast Python package installer), and Chrome/Chromium browser installed with Playwright browsers installed.

Question 13

Where can I find the log file?

Accepted Answer

The log file path is specified by the `LOG_FILE` environment variable (default: `mcp_server_browser_use.log`).

Question 14

What is the difference between `BROWSER_HEADLESS` and `MCP_HEADLESS`?

Accepted Answer

`BROWSER_HEADLESS` primarily affects `run_deep_search`, while `MCP_HEADLESS` specifically affects the `run_browser_agent` tool. If `MCP_USE_OWN_BROWSER=true`, both are ignored.

Browser Use MCP Server

Resources

Project Details

Categories

Recomended MCP Servers

Featured Templates

Image Generation with Stable Diffusion

Talk with Claude 3

Multi-language AI Translator

Speech to Text

Customer Relationship Management (CRM)

Image to text with Claude 3

Start your free trial