OpenBrowser is a framework for intelligent browser automation that utilizes the Chrome DevTools Protocol and a CodeAgent architecture to autonomously navigate, interact with, and extract information from web pages.
From the registry: AI browser automation. Write async Python to navigate, click, type, and extract data.

Please install the `openbrowser-ai` MCP server into my current AI client (that's you).
Optional prerequisites:
- Chromium-based browser — Auto-detects Chrome/Edge/Brave/Chromium. If none found and uvx is available, Chromium is installed on first run.
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["openbrowser-ai","--mcp"]
- optional environment variables:
- `OPENBROWSER_HEADLESS`: Run browser without GUI. (example: `true`)
- `OPENBROWSER_ALLOWED_DOMAINS`: Comma-separated domain whitelist.
- `OPENBROWSER_MAX_OUTPUT`: Max output characters per execution. (example: `10000`)
Note: MCP client provides intelligence — no LLM API keys required for the MCP mode. Single `execute_code` tool runs Python code in a persistent browser session.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GOOGLE_API_KEYrequiredAPI key for Google servicesOPENAI_API_KEYrequiredAPI key for OpenAI servicesANTHROPIC_API_KEYrequiredAPI key for Anthropic servicesGROQ_API_KEYrequiredAPI key for Groq servicesAWS_ACCESS_KEY_IDrequiredAWS access key IDAWS_SECRET_ACCESS_KEYrequiredAWS secret access keyAWS_DEFAULT_REGIONrequiredDefault AWS regionAZURE_OPENAI_API_KEYrequiredAPI key for Azure OpenAI servicesAZURE_OPENAI_ENDPOINTAI-powered browser automation — navigate, click, fill forms, and extract data from any website.