Compare · Browser Automation
Playwright vs Playwright MCP Server
Playwright exposes 25 tools and adds about 3,710 tokens to every model turn. Playwright exposes 33 tools and adds about 2,920. Playwright costs 1.3× as much context. Measured by connecting to each server and counting its tool list, not from the README.
 Playwrightmicrosoft |  Playwrightexecuteautomation | |
|---|---|---|
| Context tax | ~3,710 tok/turn | ~2,920 tok/turn(leaner) |
| Tools | 25 | 33 |
| Cost per 1,000 turns (Claude Sonnet 5.5, uncached) | $7.42 | $5.84 |
| Security score | 100/100 | 97/100 |
| Cold start | 965 ms | 1,494 ms |
| Runs | Local (stdio) | Local (stdio) |
| Needs keys | None declared | None declared |
| Freshness | Active | Stale |
| GitHub stars | 38k | 5.7k |
| License | Apache-2.0 | MIT |
| Official MCP registry | Yes | No |
Install in Claude Code
Playwright
claude mcp add playwright -- npx -y @playwright/mcp
Playwright
claude mcp add playwright-executeautomation -- npx -y @executeautomation/playwright-mcp-server
Tools
By name, from each server's live tool list. The same name can still behave differently.
Only in Playwright · 25
- browser_close
- browser_resize
- browser_console_messages
- browser_handle_dialog
- browser_emulate_media
- browser_evaluate
- browser_file_upload
- browser_drop
- browser_find
- browser_fill_form
- browser_press_key
- browser_type
- browser_navigate
- browser_navigate_back
- browser_network_requests
- browser_network_request
- browser_run_code_unsafe
- browser_take_screenshot
- browser_snapshot
- browser_click
- browser_drag
- browser_hover
- browser_select_option
- browser_tabs
- browser_wait_for
In both · 0
- none
Only in Playwright · 33
- start_codegen_session
- end_codegen_session
- get_codegen_session
- clear_codegen_session
- playwright_navigate
- playwright_screenshot
- playwright_click
- playwright_iframe_click
- playwright_iframe_fill
- playwright_fill
- playwright_select
- playwright_hover
- playwright_upload_file
- playwright_evaluate
- playwright_console_logs
- playwright_resize
- playwright_close
- playwright_get
- playwright_post
- playwright_put
- playwright_patch
- playwright_delete
- playwright_expect_response
- playwright_assert_response
- playwright_custom_user_agent
- playwright_get_visible_text
- playwright_get_visible_html
- playwright_go_back
- playwright_go_forward
- playwright_drag
- playwright_press_key
- playwright_save_as_pdf
- playwright_click_and_switch_tab
Questions
- Which uses fewer tokens, Playwright or Playwright?
- Playwright: its tool definitions take about 2,920 tokens per turn against 3,710 for Playwright (1.3× more). Tool definitions are resent on every model turn.
- Do Playwright and Playwright have the same tools?
- No tool names overlap: Playwright has 25 tools and Playwright has 33.
- Are Playwright and Playwright hosted or local?
- Playwright: local (stdio). Playwright: local (stdio).
Token counts use the o200k tokenizer on each server's tool definitions as an agent receives them; clients that load tools lazily pay less. Prices are Claude Sonnet 5.5 input at $2/MTok. Want to check one yourself? Run npx mcpskillhub test <package> — how it works.