Skip to main content

Tools

playwright-mcp

39,980

Playwright Model Context Protocol server from Microsoft.

Prevention Post-generation Fully autonomous Program Stable Activity band D Environment
Activity band details

Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.

Computed band: D (raw score 4.34). Shown band: D .

Facets: documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=0recent_push=2stars=1.84

Source of truth: pipeline/maturity/score.py

Description

Microsoft Playwright MCP is the official MCP server wrapping Playwright. Exposes a controlled set of browser actions to LLM agents (click, type, navigate, screenshot) through MCP, so agent access to the browser is channelled through an auditable tool interface.

Why it's included

Environment-gate for browser-using agents: MCP-mediated access rather than direct CDP, enabling per-tool allow-lists + auditing.

Addresses failure modes

These tags are the catalog's claim about what playwright-mcp is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured playwright-mcp, so none of these tags is tested here.

  • Scope creep — Actions outside declared task boundary.

Techniques

mcp-serverplaywright-wrapperbrowser-actions

View raw YAML on GitHub →