Overview
YetiBrowser MCP is a fully open-source implementation of the Browser MCP workflow. It links a Node-based MCP server with Chrome/Firefox extensions so Model Context Protocol clients—Codex/Claude Code, Cursor, Windsurf, MCP Inspector, or your own tools—can automate a real browser tab while keeping every byte on your machine and auditable. The project emphasizes transparency and hackability—no blob downloads; data stays local; and cross-browser support through shared logic for Chrome and Firefox packaging. It provides developer-focused tooling such as richer console capture, DOM diffing, page-state dumps, and full-page screenshots to facilitate debugging and QA. Production-friendly scaffolding includes packaging and publishing scripts and IDE integration. The MCP tools list exposes a rich command set (navigate, snapshot, diff, wait, click, type, fill form, screenshot, console logs, page state, and more) that lets clients automate realistic user interactions and inspect page behavior while maintaining a local, auditable workflow.
Features
browser_snapshot
capture an accessibility-oriented snapshot of the current page
browser_snapshot_diff
compare the two most recent snapshots to highlight DOM/ARIA changes
browser_navigate
load a new URL in the connected tab and return an updated snapshot
browser_screenshot
capture a viewport or full-page screenshot via the DevTools protocol
browser_get_console_logs
return recent console output, including errors with stack traces
browser_page_state
dump forms, storage keys, and cookies for the connected page
browser_evaluate
run custom JavaScript inside the page and return JSON-serializable results
browser_handle_dialog
accept or dismiss alert/confirm/prompt dialogs with optional prompt text
Who Is This For?
- MCP clients:Connect MCP clients to a local browser tab via the MCP server.
- Extension devs:Build and package cross-browser extensions that talk to the MCP server.
- Automation tools:Automation tools that connect via MCP bridge to control browser tabs.
