Playwright MCP vs Browser Use (MCP mode)
Both are browser automation MCP servers, and we ran both through the same test (click reveal) in each app. Playwright MCP passed 4 of 4 apps we tested it in; Browser Use (MCP mode) passed 0 of 4.
Test results side by side
| Playwright MCP | Browser Use (MCP mode) | |
|---|---|---|
| Claude Code | Passed 2026-10-13 | Failed 2026-10-13 |
| Cursor | Passed 2026-10-13 | Failed 2026-10-13 |
| Claude Desktop | Passed 2026-10-14 | Failed 2026-10-14 |
| ChatGPT (Codex) | Passed 2026-10-14 | Failed 2026-10-14 |
| Tools exposed (protocol check) | 25 tools | 16 tools |
| GitHub stars | 38,149 | 117,991 (shared repo) |
| License | Apache-2.0 | MIT |
| Last push | 2026-10-08 | 2026-10-09 |
Results from our own harness runs, dated per cell. Stars and last push from GitHub at our last data refresh. We don’t pick a winner here: which one fits depends on your app and setup.
What each does
Playwright MCP: Microsoft's browser automation server: the agent drives a real browser through the page's accessibility tree.
Browser Use (MCP mode): Description written after our first hands-on test.