openbrowser ai MCP
v0.1.54me.openbrowser/openbrowser-ai
AI browser automation. Write async Python to navigate, click, type, and extract data.
transport:stdio
runtime:pypi
Target client
run in your project directory
claude mcp add openbrowser-ai -e OPENBROWSER_HEADLESS=<OPENBROWSER_HEADLESS> -e OPENBROWSER_ALLOWED_DOMAINS=<OPENBROWSER_ALLOWED_DOMAINS> -e OPENBROWSER_USER_DATA_DIR=<OPENBROWSER_USER_DATA_DIR> -e OPENBROWSER_STORAGE_STATE=<OPENBROWSER_STORAGE_STATE> -e OPENBROWSER_COMPACT_DESCRIPTION=<OPENBROWSER_COMPACT_DESCRIPTION> -e OPENBROWSER_MAX_OUTPUT=<OPENBROWSER_MAX_OUTPUT> -e ANONYMIZED_TELEMETRY=<ANONYMIZED_TELEMETRY> -- uvx openbrowser-ai
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.