268 tokens across 6 tools — lean (< 1K). Measured 2026-08-18 under methodology v1.0.
| server (self-reported) | sqlite v0.1.0 |
| status | measured |
| tokenizer | tiktoken / o200k_base |
| launch command | uvx --with "mcp\<2" mcp-server-sqlite --db-path /tmp/test.db |
| 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 | d432983abc546eac2725c9db1a07f5f8dad0e6cbfb12f925c1d4fb61743d1c6b |
| category | official-reference |
| source | https://github.com/modelcontextprotocol/servers-archived |
| tool | tokens | share | description | schema |
|---|---|---|---|---|
| write_query | 50 | 18.7% | 13 | 26 |
| describe_table | 49 | 18.3% | 8 | 30 |
| append_insight | 49 | 18.3% | 7 | 30 |
| read_query | 46 | 17.2% | 8 | 27 |
| create_table | 45 | 16.8% | 8 | 26 |
| list_tables | 28 | 10.4% | 7 | 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/sqlite/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.