581 tokens across 3 tools — lean (< 1K). Measured 2026-08-16 under methodology v1.0.
| server (self-reported) | mcp-clickhouse v2.14.7 |
| status | measured |
| tokenizer | tiktoken / o200k_base |
| launch command | uvx mcp-clickhouse |
| 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 | CLICKHOUSE_HOST, CLICKHOUSE_USER, CLICKHOUSE_PASSWORD |
| canonical SHA-256 | d266049ab550225c0ca1055960d43f29c64b3e7cf03fa1241e633f9b2049f240 |
| category | vendor-official |
| source | https://github.com/ClickHouse/mcp-clickhouse |
| tool | tokens | share | description | schema |
|---|---|---|---|---|
| list_tables | 370 | 63.7% | 191 | 104 |
| run_query | 133 | 22.9% | 50 | 19 |
| list_databases | 79 | 13.6% | 5 | 9 |
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/clickhouse/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.