A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots, providing browser automation capabilities without requiring screenshots or visually-tuned models.
Path to save recording files
./recordings
Run browser in headless mode (headed by default)
Recording format, possible values: mp4, webm
mp4
Comma-separated list of capabilities to enable, possible values: tabs, pdf, history, wait, files, install
Record browser interactions as video
CDP endpoint to connect to
Browser or Chrome channel to use. Possible values: chrome, firefox, webkit, msedge, chrome-beta, chrome-canary, chrome-dev, msedge-beta, msedge-canary, msedge-dev
chrome
Path to the browser executable
Port to listen on for SSE transport
Path to the user data directory
Run server that uses screenshots (Aria snapshots are used by default)
Security Notice
Your environment variables and credentials are securely stored and encrypted. LangDB never shares these configuration values with third parties.
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!