Connects to Google's Gemini API using the Google API key for AI-driven browser automation tasks
Provides integration with Ollama's local LLM hosting service, supporting customizable context settings and model parameters for browser automation
Integrates with OpenAI's API for LLM functionality, enabling AI-powered browser control with customizable parameters
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@browser-use MCP server search for flights from New York to London next week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Project Note: This MCP server implementation builds upon the browser-use/web-ui foundation. Core browser automation logic and configuration patterns are adapted from the original project.
AI-driven browser automation server implementing the Model Context Protocol (MCP) for natural language browser control.
🧠 MCP Integration - Full protocol implementation for AI agent communication
🌐 Browser Automation - Page navigation, form filling, and element interaction
👁️ Visual Understanding - Screenshot analysis and vision-based interactions
🔄 State Persistence - Maintain browser sessions between tasks
🔌 Multi-LLM Support - OpenAI, Anthropic, Azure, DeepSeek integration
Related MCP server: Cloudflare Playwright MCP
Python 3.11 or higher
uv (fast Python package installer)
Chrome/Chromium browser
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"browser-use": {
"command": "uvx",
"args": [
"mcp-server-browser-use",
],
"env": {
"OPENROUTER_API_KEY": "",
"OPENROUTER_ENDPOINT": "https://openrouter.ai/api/v1",
"OPENAI_ENDPOINT": "https://api.openai.com/v1",
"OPENAI_API_KEY": "",
"ANTHROPIC_ENDPOINT": "https://api.anthropic.com",
"ANTHROPIC_API_KEY": "",
"GOOGLE_API_KEY": "",
"AZURE_OPENAI_ENDPOINT": "",
"AZURE_OPENAI_API_KEY": "",
"DEEPSEEK_ENDPOINT": "https://api.deepseek.com",
"DEEPSEEK_API_KEY": "",
"MISTRAL_API_KEY": "",
"MISTRAL_ENDPOINT": "https://api.mistral.ai/v1",
"OLLAMA_ENDPOINT": "http://localhost:11434",
"ANONYMIZED_TELEMETRY": "true",
"BROWSER_USE_LOGGING_LEVEL": "info",
"CHROME_PATH": "",
"CHROME_USER_DATA": "",
"CHROME_DEBUGGING_PORT": "9222",
"CHROME_DEBUGGING_HOST": "localhost",
"CHROME_PERSISTENT_SESSION": "false",
"BROWSER_HEADLESS": "false",
"BROWSER_DISABLE_SECURITY": "false",
"BROWSER_WINDOW_WIDTH": "1280",
"BROWSER_WINDOW_HEIGHT": "720",
"BROWSER_TRACE_PATH": "trace.json",
"BROWSER_RECORDING_PATH": "recording.mp4",
"RESOLUTION": "1920x1080x24",
"RESOLUTION_WIDTH": "1920",
"RESOLUTION_HEIGHT": "1080",
"VNC_PASSWORD": "youvncpassword",
"MCP_MODEL_PROVIDER": "anthropic",
"MCP_MODEL_NAME": "claude-3-5-sonnet-20241022",
"MCP_TEMPERATURE": "0.3",
"MCP_MAX_STEPS": "30",
"MCP_USE_VISION": "true",
"MCP_MAX_ACTIONS_PER_STEP": "5",
"MCP_TOOL_CALL_IN_CONTENT": "true"
}
}"browser-use": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-browser-use",
"run",
"mcp-server-browser-use"
],
"env": {
...
}
}# Install dev dependencies
uv sync
# Run with debugger
npx @modelcontextprotocol/inspector uv --directory . run mcp-server-browser-useBrowser Conflicts: Close all Chrome instances before starting.
API Errors: Verify API keys in environment variables match your LLM provider.
Vision Support: Ensure MCP_USE_VISION=true for screenshot analysis.
The server supports multiple LLM providers through environment variables. Here are the available options for MCP_MODEL_PROVIDER:
Provider | Value | Required Env Variables |
Anthropic |
|
|
OpenAI |
|
|
Azure OpenAI |
|
|
DeepSeek |
|
|
Gemini |
|
|
Mistral |
|
|
Ollama |
|
|
OpenRouter |
|
|
For endpoints marked as optional, default values will be used if not specified
Temperature can be configured using MCP_TEMPERATURE (default: 0.3)
Model can be specified using MCP_MODEL_NAME
For Ollama models, additional context settings like num_ctx and num_predict are configurable
This project extends the browser-use/web-ui under MIT License. Special thanks to the original authors for their browser automation framework.
MIT - See LICENSE for details.
Handle run-browser-agent tool calls.
| Name | Required | Description | Default |
|---|---|---|---|
| add_infos | No | ||
| task | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure but fails completely. It doesn't indicate whether this is a read or write operation, what side effects it might have, what permissions are required, or what the expected behavior is. The phrase 'Handle... tool calls' is too vague to convey any meaningful behavioral information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
While the description is technically concise (only 5 words), this represents under-specification rather than effective brevity. The single sentence doesn't earn its place by providing meaningful information. A truly concise description would still convey essential purpose and usage information in minimal words, which this fails to do.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a tool with 2 parameters, no annotations, no output schema, and 0% schema description coverage, the description is completely inadequate. It provides no information about what the tool does, how to use it, what parameters mean, or what to expect from its operation. The description fails to compensate for any of the missing structured information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, meaning neither parameter has any description in the schema. The tool description provides no information about what the 'task' or 'add_infos' parameters mean, what format they should take, or how they affect the tool's operation. For a tool with 2 parameters and zero schema documentation, this represents a complete failure to add parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Handle run-browser-agent tool calls' is essentially a tautology that restates the tool name without explaining what the tool actually does. It doesn't specify what 'run-browser-agent' means, what resources it operates on, or what action it performs. While it mentions 'tool calls', this adds no meaningful information beyond the name itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides absolutely no guidance on when to use this tool, what context it's appropriate for, or what alternatives might exist. There are no sibling tools mentioned, but even for a standalone tool, the description fails to give any indication of its intended use case or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0run_browser_agentWith only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'run_browser_agent' has a distinct purpose that cannot be confused with any other tool in this set.
The naming pattern cannot be inconsistent with only one tool. The tool name 'run_browser_agent' follows a clear verb_noun pattern, and there are no other tools to create naming conflicts or mixed conventions.
A single tool is generally too few for most server purposes, as it limits functionality and may not cover the domain adequately. For a browser automation server, one tool feels thin and restrictive compared to typical expectations of multiple actions like navigation, clicking, or form filling.
The tool surface is severely incomplete for browser automation. With only one tool to run an agent, there are obvious gaps in core operations such as navigating to URLs, interacting with page elements, extracting data, or managing browser sessions, which will likely cause agent failures in practical use.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/deploya-labs/mcp-browser-use'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
