mcp-context-cost

playwright — context cost

4,024 tokens across 24 tools — light (1–5K). Measured 2026-08-16 under methodology v1.0.

   
server (self-reported) Playwright v1.63.0-alpha-2026-08-05
status measured
tokenizer tiktoken / o200k_base
launch command npx -y @playwright/mcp@latest
isolation docker · public.ecr.aws/docker/library/node:22-slim · network bridge · network enabled for package fetch; clean FS, no host credentials
env vars supplied none
canonical SHA-256 5d5d92a7c727ef75bd9a70f076039dbdbfd331c56f022915c2e89b76f7fc88f0
category vendor-official
source https://github.com/microsoft/playwright-mcp

Where the tokens are

tool tokens share description schema
browser_take_screenshot 329 8.2% 23 268
browser_fill_form 255 6.3% 4 214
browser_drop 243 6.0% 34 169
browser_find 221 5.5% 63 121
browser_network_request 207 5.1% 33 136
browser_click 205 5.1% 6 164
browser_run_code_unsafe 202 5.0% 26 133
browser_type 198 4.9% 5 157
browser_evaluate 184 4.6% 8 138
browser_network_requests 184 4.6% 24 123
browser_snapshot 184 4.6% 13 135
browser_drag 183 4.5% 7 140
browser_console_messages 181 4.5% 4 139
browser_select_option 162 4.0% 6 119
browser_tabs 154 3.8% 12 107
browser_wait_for 128 3.2% 13 78
browser_hover 122 3.0% 5 81
browser_handle_dialog 112 2.8% 3 71
browser_file_upload 111 2.8% 5 69
browser_press_key 110 2.7% 6 66
browser_resize 107 2.7% 4 66
browser_navigate 92 2.3% 4 49
browser_navigate_back 78 1.9% 9 31
browser_close 70 1.7% 3 31

Each tool is tokenized on its own, so the parts do not sum exactly to the whole: the array adds its own brackets and commas, and the tokenizer merges tokens across object boundaries. The badge number is always the count of the whole array, never a sum of parts.

Re-derive it

npx -y mcp-context-cost verify results/playwright/measurement.json

That re-tokenizes the published capture and checks the count and the hash. If it disagrees with the badge, the badge is wrong — open an issue and it gets corrected.

Badge JSON · All servers · Leaderboard · Methodology