microsoft/playwright-mcp
Browser automation as agent tools, built on Playwright's accessibility tree rather than screenshots: structured, deterministic web interaction for agents. Agentiquette scores it 80/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Tool collection (MCP) |
|---|---|
| License | Apache-2.0 |
| Maintainer | Microsoft |
| Compatible agents | claude-code, cursor, codex, copilot, generic |
| File patterns | |
| Triggering | manual-reference |
| GitHub metrics | 34,797 stars · 2,882 forks · 2 open issues (fetched 2026-07-07) |
| Last commit | 2026-06-29 |
| Created | 2025-03-21 |
Editorial analysis
The accessibility-tree decision is why this entry scores where it does: structured snapshots make agent web interaction deterministic and cheap where screenshot-based approaches are probabilistic and heavy. Two open issues against this adoption is the cleanest maintenance signal in the index. The QA loops documented on this site lean on exactly this class of tool.
Risks
A browsing agent is an injection surface: pages it reads can carry instructions. Sandbox accordingly.
Evidence notes: Reliability: deterministic tree snapshots vs pixel guessing. Maintenance: 2 open issues at fetch. Safety: sandboxing documented, injection surface acknowledged in docs.
Install and first run
npx @playwright/mcp@latestAlternatives in this category
The reference implementations of the Model Context Protocol: the official server collection that defines what a well-built agent tool looks…
An MCP toolkit that gives coding agents semantic code retrieval and editing: language-server-grade symbol operations instead of…
An MCP server that feeds agents current, version-specific library documentation at generation time, attacking the stale-training-data class…
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/playwright-mcp)Frequently asked questions
Is microsoft/playwright-mcp good?
microsoft/playwright-mcp scores 80/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is microsoft/playwright-mcp for?
Browser automation as agent tools, built on Playwright's accessibility tree rather than screenshots: structured, deterministic web interaction for agents.
Is microsoft/playwright-mcp maintained?
Last commit 2026-06-29, 2 open issues at fetch time (2026-07-07). Maintenance is scored at 88 of 100.
Maintainer of microsoft/playwright-mcp? Claim this listing and suggest corrections.