359 tokens across 3 tools — lean (< 1K). Measured 2026-08-16 under methodology v1.0.
| server (self-reported) | DeepWiki v2.14.3 |
| status | measured |
| tokenizer | tiktoken / o200k_base |
| launch command | npx -y mcp-remote https://mcp.deepwiki.com/mcp |
| 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 | 3735162916165ab23696fc91fbf626bd99a36ddcd1e15746e91e16c7e336b379 |
| category | vendor-official |
| source | https://docs.devin.ai/work-with-devin/deepwiki-mcp |
| tool | tokens | share | description | schema |
|---|---|---|---|---|
| ask_question | 148 | 41.2% | 19 | 76 |
| read_wiki_structure | 108 | 30.1% | 12 | 41 |
| read_wiki_contents | 104 | 29.0% | 8 | 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/deepwiki/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.