BrowserTools MCP

Three-part system (Chrome extension + Node.js server + MCP server) that lets AI coding assistants monitor browser console logs, network traffic, take screenshots, analyze DOM elements, and run Lighthouse-based audits for accessibility, performance, SEO, and best practices directly from MCP-compatible IDEs.

Evaluated Mar 07, 2026 (0d ago) v1.2.0
Homepage ↗ Repo ↗ Developer Tools browser devtools console-logs network-monitoring screenshots accessibility seo performance-audit cursor mcp chrome-extension
⚙ Agent Friendliness
72
/ 100
Can an agent use this?
🔒 Security
72
/ 100
Is it safe for agents?
⚡ Reliability
65
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
70
Error Messages
55
Auth Simplicity
78
Rate Limits
65

🔒 Security

TLS Enforcement
85
Auth Strength
70
Scope Granularity
65
Dep. Hygiene
78
Secret Handling
65

Browser automation/CDP MCP. Controls browser — high risk for credentials exposure. Sandbox browsing context. Clear cookies/sessions between agent sessions.

⚡ Reliability

Uptime/SLA
65
Version Stability
68
Breaking Changes
62
Error Recovery
65
AF Security Reliability

Best When

You're developing web applications in an MCP-compatible IDE (Cursor, Cline, Zed) and want your AI assistant to see browser logs, network traffic, screenshots, and audit results to help debug and improve your application.

Avoid When

You need production monitoring, work exclusively in non-Chrome browsers, want browser automation for scraping, or use an IDE without MCP support.

Use Cases

  • Debugging web applications with AI assistants by sharing browser console logs
  • Monitoring network requests and responses during development
  • Taking and auto-pasting browser screenshots into IDE for AI analysis
  • Running accessibility (WCAG) audits from within the IDE
  • Performance bottleneck identification via Lighthouse integration
  • SEO evaluation and optimization with AI guidance
  • NextJS-specific debugging for app router and page router

Not For

  • Production browser monitoring or APM
  • Automated browser testing in CI/CD pipelines
  • Web scraping or data extraction
  • Non-Chrome browsers (requires Chrome extension)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication required. All data remains local. Sensitive headers and cookies are stripped before processing to prevent LLM exposure.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

Fully open source under MIT license. No commercial tiers or paid features.

Agent Metadata

Pagination
unknown
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • Requires three separate components running simultaneously (Chrome extension, Node server, MCP server)
  • Chrome extension must be manually installed from GitHub releases
  • WebSocket connection between Chrome extension and Node server can disconnect
  • Token limits and truncation settings need tuning to avoid overwhelming LLM context
  • Only works with Chrome browser - no Firefox/Safari support
  • Screenshot auto-paste feature is Cursor-specific
  • Puppeteer dependency may conflict with other browser automation tools

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for BrowserTools MCP.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-07.

6470
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered