YetiBrowser MCP 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 MCP server?

YetiBrowser MCP is a fully open-source solution to allow AI assistants to easily interact with your existing browser. That is what the yetibrowser mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

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

The tools it exposes

The server publishes 14 tools. What each one is for:

  • 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_wait — pause automation for a set number of seconds
  • browser_wait_for — block until a selector appears (optionally visible) before proceeding
  • browser_press_key — simulate a keyboard key press on the focused element
  • browser_click — click the element identified by a CSS selector
  • browser_hover — hover the pointer over the targeted element
  • browser_drag — drag an element onto a drop target for sortable/drag-and-drop UIs
  • browser_type — type text (optionally submitting with Enter) into an editable element
  • browser_fill_form — fill multiple inputs/selects/checkboxes/radios in a single call
  • browser_select_option — choose one or more options in a element

Getting it running

Installation goes through your MCP client rather than a global install: point it at @yetidevworks/server on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. YetiBrowser MCP's toolset — browser_snapshot, browser_snapshot_diff, browser_navigate and 11 more — is a fair guide to whether it matches your workflow.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch YetiBrowser MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

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 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

It connects YetiBrowser MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (browser_snapshot, browser_snapshot_diff, browser_navigate, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with YetiBrowser MCP directly.