Tier lists / Browser & computer-use agents / Playwright MCP
A
84
/ 100
Microsoft's MCP server that lets agents drive a real browser via Playwright accessibility snapshots.
Use it when…
You want Claude Code/Cursor to test and click through your web app.
Skip it if…
You need a hosted, scalable browser fleet.
Score breakdown
Initial editorial estimate from public info; not yet hands-on tested. How we score →
Details
- Pricing
- Free and open sourceUnverified. Unverified: editorial summary. We couldn't confirm this on an official pricing page (JS-rendered, no public pricing, or usage-based) as of Oct 18, 2026.
- Free tier
- Yes (unverified)
- Platforms
- MCP · CLI
- Open source
- Yes
- Official URL
- https://github.com/microsoft/playwright-mcp
- URL verified
- Oct 18, 2026 (curl HTTP GET)
- Last reviewed
- Oct 18, 2026 by agent
- Sources
Changelog
- Oct 18, 2026: Initial listing; score 84 (A) as editorial estimate.
Alternatives for this job
A Open-source library to let AI control browsers
83/100 open free tier
A Headless browser infrastructure for agents
79/100 free tier
A AI browser automation SDK
78/100 open free tier
See all Playwright MCP alternatives, including free and open-source options →
Compare Playwright MCP
- Playwright MCP vs Browser Use (A-tier)
- Playwright MCP vs Browserbase (A-tier)
- Playwright MCP vs Stagehand (A-tier)
- Playwright MCP vs Skyvern (B-tier)
Featured in these guides
- Best AI browser agents and browser automation tools
- Best open-source browser automation tools for AI agents
- Best MCP servers for developers
- Best tools to use with Claude Code, Codex and Cursor
Get your badge
Make Playwright MCP? Show its current tier on your site or README. The badge updates automatically when the score changes. About badges →
