MCP100 verdict
Let AI clients inspect and automate web browsers with Playwright.
MCP100 Assessment
Editorial verdict
Let AI clients inspect and automate web browsers with Playwright.
Reviewed 2026-07-24 · Next review 2026-10-24
Task Fit
Mapped
Specialized workflows
Trust
Reviewed
A dated editorial review is published on the MCP detail page.
Maintenance
Activity observed
A dated repository or package update is available; editorial maintenance review is still pending.
Popularity
Signals available
Visible usage signals are shown for discovery only, not as proof of safety.
Best for
- Inspecting and testing web interfaces through accessibility snapshots
- Reproducing browser journeys in a dedicated test profile
Not ideal for
- API-only testing that does not need a browser
- Unattended access to a personal browsing profile
Avoid if
- The workflow cannot permit an agent to navigate, type, click, upload files, or read page content
- You cannot isolate sensitive authenticated sessions from the agent-controlled browser
Trade-offs
- A persistent profile is convenient but can retain cookies and authenticated state between sessions.
- Origin allow/block options reduce accidental access but the publisher explicitly says they are not a security boundary.
Evidence scope
Evidence
Popularity
36.1k MCP repository stars
6.4M package downloads
Stars observed 2026-08-14T18:46:26.000Z · Downloads observed 2026-07-29T17:30:00.000Z
Exact implementation repository metric.
Exact implementation package metric.
Maintenance
Publisher activity observed 2026-08-12T20:16:20Z
Current source snapshot
Trust review
Source relationship: First-party MCP
Reviewed 2026-07-24 · Next review 2026-10-24