AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Browser Automation/
browser-tools-mcp
browser-tools-mcp logo

browser-tools-mcp

Active·★ 7.3k·MIT·Updated 2026-10-16
★ Trending

BrowserTools MCP is a browser monitoring and interaction tool that lets MCP-capable AI applications capture and analyse browser data through a Chrome extension. It has three components: a Chrome extension that captures screenshots, console logs, network activity (XHR requests and responses) and selected DOM elements, a Node server that sits between the extension and the MCP server, and the MCP server that exposes standard tools to clients such as Cursor, Claude Desktop, Cline or Zed. The server intelligently truncates strings and duplicate objects to stay within token limits.

Version 1.2.0 added an option to auto-paste screenshots into Cursor, Lighthouse-based tools for SEO, performance, accessibility and best-practice audits, a Next.js-specific SEO prompt, a Debugger Mode and an Audit Mode that run their tools in sequence, fixes for Windows connectivity, and auto-discovery and auto-reconnect between the server, extension and MCP server. Setup is to install the extension from the release zip, run the MCP server with npx, and open the DevTools panel. The README states that all logs are stored locally and never sent to any third-party service. The project is MIT licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-17.

License
MIT
Latest release
v2.0.2 · 2026-08-12
Last commit
2026-10-16
Contributors
7
Forks
541
Open issues and PRs
4
First published
2025-02-10
npm package
@agentdeskai/browser-tools-mcp 2.0.2 · 3,108 downloads last week

Source: GitHub, npm and PyPI public APIs.

#Browser Automation#AI Tools#Model Context Protocol#Web Audits#Chrome Extension#Web Browsing#Coding
$ Install
$ npx @agentdeskai/browser-tools-mcp@latest
↗ Visit site★ GitHub
01

Features

01Capture browser data (logs, network, DOM, screenshots)
02Integrate with AI via Model Context Protocol (MCP)
03Perform comprehensive web development audits (SEO, Accessibility, Performance)
04Automate headless Chrome for audit data collection
05Provide structured JSON results for AI interpretation
02

Why choose it

+Gives an assistant the browser context a developer would check: console logs, network requests, the selected element and screenshots.
+Lighthouse-based audit tools for SEO, performance, accessibility and best practices, plus Debugger and Audit modes.
+Logs stay on your machine (the README says they are never sent to third parties) and are truncated to fit token limits.
+Works with Cursor, Claude Desktop, Cline and Zed, with auto-reconnect between components.
03

Trade-offs

!You must set up three parts: the Chrome extension, the Node server and the MCP server, and keep them connected.
!It is tied to Chrome through its extension, and the README's auto-paste feature targets Cursor.
!The repository was last updated in August 2026 and the README is still described at v1.2.0.
05

Maintenance check

ActiveChecked: 2026-10-22
Last commit
2026-10-16
Commits, last 90 days
58
Releases, last 90 days
2
Latest release
v2.0.2 (2026-08-12)
Open issues
2
Recent issues with at least one comment
17/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 7, 14, 0, 0, 0, 0, 0, 0, 0, 3, 31, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

04

Who it fits

Pick it if
  • You use Cursor or a similar IDE agent and want it to read console logs, network activity, screenshots and the currently selected DOM element from your own Chrome.
  • You want Lighthouse-based audits for accessibility, performance, SEO and best practices from within the agent.
  • You want browser logs kept local: the README says logs are stored on your machine and never sent to a third-party service.
Look elsewhere if
  • You want the agent to click through and drive pages; this tool is aimed at monitoring and auditing, not full automation.
  • You do not want to install a Chrome extension and run a separate local Node server alongside the MCP server.
  • You want the most actively developed option: the latest release in the data we checked was v2.0.2 on 2026-08-12.
06

How it differs

chrome-devtools-mcp logovs chrome-devtools-mcp★ 54.0k

Chrome DevTools MCP now covers similar ground (performance traces, network and console inspection, screenshots) from the Chrome team, with fewer moving parts. Browser Tools MCP's distinguishing points are its Lighthouse audit tools and its use of your already-open browser through an extension.

Full comparison →
07

Compatibility

Cursor
Native Integration
Verified via docs
Claude Desktop
Supported
Verified via docs
Cline
Supported
Verified via docs
Zed
Supported
Verified via docs
Model Context Protocol
Protocol Native
Verified via docs
08

Quick start

1
$ npx @agentdeskai/browser-tools-mcp@latest
09

Use cases

↳Enable AI coding agents to audit and debug web pages
↳Improve web application SEO, performance, and accessibility
↳Automated analysis and enhancement of NextJS applications
10

Alternatives

⚡Top VS:
VSchrome-devtools-mcp★54.0k→VSmcp-chrome★12.5k→VSmcp★7.2k→VSmcp-playwright★5.7k→
chrome-devtools-mcp logo
chrome-devtools-mcp★ 54.0k
Chrome DevTools for coding agents
VSCompare→
mcp-chrome logo
mcp-chrome★ 12.5k
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
VSCompare→
mcp logo
mcp★ 7.2k
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
VSCompare→
mcp-playwright logo
mcp-playwright★ 5.7k
Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌
VSCompare→
browser-agent-py logo
browser-agent-py★ 1.6k
AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.
VSCompare→
playwright-mcp logo
playwright-mcp★ 38.5k
Playwright MCP server
VSCompare→
nanobrowser logo
nanobrowser★ 14.2k
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
VSCompare→
firecrawl-mcp-server logo
firecrawl-mcp-server★ 7.7k
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
VSCompare→
See all alternatives →

Featured in these lists

  • Best MCP Servers for Browser Automation

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
AgentDeskAI /
browser-tools-mcp
↗

Chrome extension and MCP server that let AI tools read your browser's logs, network and DOM

7.3k541MIT
Last commit1w ago
StatusActive
CategoryBrowser Automation
Contributors7
Latest releasev2.0.2
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.