YetiBrowser MCP

YetiBrowser MCP acts as a bridge that allows AI assistants to see and interact with a web browser just like a human would. Instead of just reading static text, an AI can now use this tool to open tabs, click buttons, fill out forms, and navigate through websites in real-time. It is designed to be completely private and transparent, keeping all browsing data on the user’s local machine while giving AI agents a set of "hands" to explore and interact with the live web. On a technical level, this solution links a Node-based Model Context Protocol server directly to browser extensions for Chrome and Firefox. It provides a robust suite of automation tools, including the ability to capture accessibility-oriented snapshots, monitor console logs for errors, and even execute custom JavaScript within a page. Developers can use it to perform complex actions like DOM diffing—which highlights exactly how a page changed after an interaction—or simulating specific keyboard and mouse events to navigate sophisticated web applications. What makes this MCP particularly valuable for developers is its "local-first" and open-source nature. Because the extension communicates only with a localhost server, sensitive browsing data never leaves the device, making it a secure choice for integrating with AI coding assistants like Claude Code, Cursor, or Windsurf. With specialized features for dumping page states, capturing full-page screenshots, and handling dialog boxes, it transforms a standard LLM into a powerful, auditable agent capable of web testing, automated research, and deep debugging.

Category: Browser & Web Automation

Tags: chrome, dom-manipulation, firefox, javascript, web-automation

Visit YetiBrowser MCP

How to install and configure YetiBrowser MCP

1. Installation Browser Extension: * Chrome: Install from the Chrome Web Store. Leave it on Automatic connection mode unless using multiple instances. * Firefox: Currently unavailable (on hold due to Manifest V3 limitations). MCP Server: The server is distributed via npm and can be run using npx. No manual global installation is required if using the commands below. ---

2. Configuration

Codex CLI (~/.codex/config.toml) Add the following entry to your configuration file: toml [mcp_servers.yetibrowser-mcp] command = "npx" args = ["yetibrowser-mcp"] Note: To specify a port, use: args = ["yetibrowser-mcp", "--ws-port", "9010"]

Claude Desktop (claude_desktop_config.json) While the text refers to a separate document for the specific JSON, based on the provided npx instructions, the standard configuration for Claude Desktop would be: json { "mcpServers": { "yetibrowser-mcp": { "command": "npx", "args": ["-y", "yetibrowser-mcp"] } } }

MCP Inspector (for testing) Run the following command to debug: bash npx @modelcontextprotocol/inspector yetibrowser-mcp -- --ws-port 9010 ---

3. Available Tools * 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_go_back / browser_go_forward: Move through browser history. * browser_wait: Pause automation for a specified number of seconds. * browser_wait_for: Block until a selector appears (optionally visible). * 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. * browser_type: Type text into an editable element (optionally submitting with Enter). * browser_fill_form: Fill multiple inputs/selects/checkboxes/radios in one call. * browser_select_option: Choose options in a <select> element. * browser_screenshot: Capture a viewport or full-page screenshot. * browser_get_console_logs: Return recent console output, including errors with stack traces. * browser_page_state: Dump forms, storage keys, and cookies for the page. * browser_connection_info: Report bridge WebSocket port, connection status, and extension version. * browser_evaluate: Run custom JavaScript inside the page and return JSON results. * browser_handle_dialog: Accept or dismiss alert/confirm/prompt dialogs. ---

4. Example Prompts * "What is the yetibrowser mcp connection info?" (Used to find the port for manual extension configuration). * "Navigate to [URL] and take a screenshot." * "Fill out the login form with [Username] and [Password]."

What you can do with YetiBrowser MCP

Use Case 1: Automated UI Regression Testing and Visual Auditing Problem: Developers and QA engineers often manually verify that UI changes haven't broken existing functionality or layout, which is time-consuming and prone to human error. Solution: YetiBrowser MCP allows an AI assistant to programmatically navigate through a web application, capture snapshots, and identify changes. The browser_snapshot_diff and browser_screenshot tools enable the AI to detect DOM or visual regressions automatically. Example: A developer asks the AI: "Navigate to the settings page, take a snapshot, then click the 'Dark Mode' toggle and tell me if any elements disappeared from the accessibility tree." The AI uses browser_navigate, browser_snapshot, browser_click, and browser_snapshot_diff to report specific UI changes.

Use Case 2: AI-Assisted Debugging of Live Web Applications Problem: When a web application behaves unexpectedly, developers must manually open DevTools, inspect the DOM, check console logs, and verify cookies or local storage. Solution: This MCP provides tools like browser_get_console_logs, browser_page_state, and browser_evaluate. An AI can "reach into" the running tab to diagnose issues based on real-time data that is usually hidden from the assistant. Example: A developer tells their AI IDE (like Cursor or Claude Code): "The checkout button isn't working on my local dev tab. Check the console logs and the current state of the Redux store." The AI runs browser_get_console_logs to find a 404 error and uses browser_evaluate to inspect the JavaScript heap or global variables.

Use Case 3: Automating Tasks within Authenticated Sessions Problem: Most AI automation tools struggle with sites behind logins (SSO, banking, internal HR portals) because they use "headless" browsers that don't share the user's cookies or active session. Solution: YetiBrowser MCP connects directly to the user's existing browser tab. Since the user is already logged in via their standard Chrome or Firefox profile, the AI can perform actions on protected pages without needing credentials. Example: A user wants to bulk-update descriptions in an internal CMS. They open the CMS in their browser and tell the AI: "Look at the list of articles on this page. For every draft, click 'Edit', paste this disclaimer into the footer field using browser_fill_form, and click 'Save'."

Use Case 4: Complex Web Data Extraction and Form Processing Problem: Scrapers often fail on complex, modern web apps that rely on heavy JavaScript, drag-and-drop interactions, or multi-step modals. Solution: The MCP provides high-level interaction tools like browser_drag, browser_wait_for, and browser_select_option. This allows…

Key facts

  • Open Source
  • https://github.com/yetidevworks/yetibrowser-mcp
  • Browser & Web Automation, Developer Tools & Code Intelligence
  • chrome, dom-manipulation, firefox, javascript, web-automation

Part of MCP Servers

Related MCP servers

  • MCP LaTeX Server — MCP LaTeX Server is an MCP server that provides tools for creating, editing, validating, and compiling LaTeX documents directly through…
  • MCP JSON — MCP JSON is an MCP server collection that bundles tools for file system operations, Google search, browser-based web automation, and…
  • MCP Jupyter Complete — MCP Jupyter Complete is an MCP server that provides tools for manipulating Jupyter notebook files through position-based cell operations and…
  • MCP LSP Go — MCP LSP Go is an MCP server that connects AI assistants to the official Go Language Server Protocol implementation, gopls,…
  • MCP Manager — MCP Manager is an MCP server management tool that connects directly to your Claude Desktop environment, enabling users to discover,…
  • MCP Lab — MCP Lab is an MCP server development environment designed for building, testing, and debugging custom Model Context Protocol servers integrated…

How do I install YetiBrowser MCP?

First, install the YetiBrowser extension from the Chrome Web Store and keep it set to Automatic connection mode. Next, add the server package @yetidevworks/server to your MCP client configuration using the npx command runner, such as in Codex config.toml or Claude Desktop configuration files, then restart the client.

What can YetiBrowser MCP do?

It provides tools to navigate URLs, capture DOM snapshots and diffs, take screenshots, read console logs, dump cookies and storage, fill forms, hover, click, drag elements, and execute custom JavaScript expressions inside an active browser tab.

Which MCP clients work with YetiBrowser MCP?

YetiBrowser MCP works with any Model Context Protocol client using standard stdio transport. Common examples include Codex CLI, Claude Code, Claude Desktop, Cursor, Windsurf, and the official MCP Inspector tool.

Is YetiBrowser MCP open source?

Yes, YetiBrowser MCP is open source. The repository layout, shared schemas, server code, and browser extensions are publicly available on GitHub under the yetidevworks organization.

Does YetiBrowser MCP support Firefox?

Support for Firefox is currently on hold. Due to limitations with Manifest V3 APIs in stable releases of Firefox, full extension functionality is temporarily unavailable outside of experimental Nightly builds.

  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories