5,074 tokens across 5 tools — moderate (5–15K). Measured 2026-08-16 under methodology v1.0.
| server (self-reported) | awslabs.aws-documentation-mcp-server v1.29.0 |
| status | measured |
| tokenizer | tiktoken / o200k_base |
| launch command | uvx awslabs.aws-documentation-mcp-server@latest |
| isolation | docker · ghcr.io/astral-sh/uv:python3.12-bookworm-slim · network bridge · network enabled for package fetch; clean FS, no host credentials |
| env vars supplied | none |
| canonical SHA-256 | 03d94c1d9bbcaf8fcaf375d1d6f14b975f108724d76ebe3d70ea7ce72eed13ac |
| category | vendor-official |
| source | https://github.com/awslabs/mcp |
| tool | tokens | share | description | schema |
|---|---|---|---|---|
| search_documentation | 1,956 | 38.5% | 657 | 239 |
| search_table | 1,361 | 26.8% | 658 | 172 |
| read_sections | 634 | 12.5% | 467 | 75 |
| read_documentation | 571 | 11.3% | 377 | 125 |
| recommend | 550 | 10.8% | 354 | 41 |
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.
npx -y mcp-context-cost verify results/aws-documentation/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.