YetiBrowser MCP Server

YetiBrowser MCP is a fully open-source solution to allow AI assistants to easily interact with your existing browser

Local serverstdioTypeScript

What is the YetiBrowser MCP Server?

YetiBrowser MCP is a fully open-source solution to allow AI assistants to easily interact with your existing browser

The short version

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.

  • Transparent and hackable — – no blob downloads. Inspect, fork, and extend every component
  • Local-first — – the extension talks only to a localhost MCP server; browsing data never leaves your device
  • Cross-browser — – shared logic powers both Chrome and Firefox packages (Firefox build is pending better Manifest V3 support, so connection UX may be limited until Mozilla ships full MV3 APIs)
  • Developer-focused tooling — – richer console capture, DOM diffing, page-state dumps, and full-page screenshots built for debugging and QA
  • Production-friendly — – scripts and docs for packaging, publishing, and integrating with IDE workflows

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
browser_snapshotcapture an accessibility-oriented snapshot of the current page
browser_snapshot_diffcompare the two most recent snapshots to highlight DOM/ARIA changes
browser_navigateload a new URL in the connected tab and return an updated snapshot
browser_waitpause automation for a set number of seconds
browser_wait_forblock until a selector appears (optionally visible) before proceeding
browser_press_keysimulate a keyboard key press on the focused element
browser_clickclick the element identified by a CSS selector
browser_hoverhover the pointer over the targeted element
browser_dragdrag an element onto a drop target for sortable/drag-and-drop UIs
browser_typetype text (optionally submitting with Enter) into an editable element
browser_fill_formfill multiple inputs/selects/checkboxes/radios in a single call
browser_select_optionchoose one or more options in a <select> element
browser_screenshotcapture a viewport or full-page screenshot via the DevTools protocol
browser_get_console_logsreturn recent console output, including errors with stack traces

How to install the YetiBrowser MCP Server

{
  "mcpServers": {
    "github-com-yetidevworks-yetibrowser": {
      "command": "npx",
      "args": ["-y", "@yetidevworks/server"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • “Use YetiBrowser MCP to browser snapshot.”
  • “Use YetiBrowser MCP to browser snapshot diff.”
  • “Use YetiBrowser MCP to browser navigate.”

Frequently asked questions

YetiBrowser MCP is a fully open-source solution to allow AI assistants to easily interact with your existing browser Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.