Enables AI clients to securely operate a local machine via MCP or REST, providing file read/write, Playwright browser automation, and shell/service administration.
Exposes a governed, OAuth-gated MCP endpoint that lets web AI clients such as Claude, ChatGPT, Grok, and Postman work directly on your local machine. It enables file reading and editing, whitelisted shell commands, search, Git and SQLite access, browser and DevTools automation, background tasks, localhost fetches, clipboard, notifications, and port management.
Turns web-based AI clients such as Claude, ChatGPT, and Grok into secure operators of a local machine by exposing an OAuth-gated MCP endpoint with 38 governed tools for file editing, whitelisted shell commands, search, Git, SQLite, browser automation, DevTools, background tasks, localhost fetches, ports, clipboard, notifications, and Postman control. Read-only and destructive operations are annotated, optional app providers can be toggled, and access is confined to permitted folders for safe, local-first desktop automation from the browser.
Enables AI assistants to securely access local machine capabilities such as file operations, shell commands, Skills, and Pi Tools through a controlled MCP interface with token authorization and multiple tunnel options.