Anki vs Context7
Context7 scores 20 points higher on the same evidence, which is a real separation rather than noise. Both are measured the same way, on the same day, from public evidence only — so this is a comparison of two measurements rather than two marketing pages. How we measure ›
| Anki | Context7 | what it means | |
|---|---|---|---|
| tashan score | 78 | 98 | upkeep + freshness, gated by adoption |
| Adoption evidence | 2k/wk | 1.1m/wk | the raw public signal the score came from |
| Last release | active | active | npm publish or repo push |
| Upkeep | 98 | 100 | cadence, maintainers, status |
| Expertise grade | deep | deep | an LLM read of its own documentation against a fixed rubric |
| Security audit | no known advisories | no known advisories, no build provenance | a summary — the full audit, free, is on each dossier |
| Licence | MIT | MIT | |
| Maintainers | more than one | more than one | bus-factor risk |
Install either
Anki
claude mcp add ankimcp-anki-mcp-server -- npx -y @ankimcp/anki-mcp-serverContext7
claude mcp add upstash-context7 -- npx -y @upstash/context7-mcpNeither score is a security verdict — "well maintained" and "nothing known is wrong" are different claims, which is why the audit is a separate row and never folded into the number. The full audit for each — the advisory ids, the version that fixes them and anything that runs at install time — is free on its own page: Anki · Context7.
Both numbers above are today’s. Whichever you pick, the question that matters next is when it changes — and this page cannot know that. Pro keeps the series behind each capability, and names what to move to.
- The whole series behind any row, back to the first day we measured it
- The replacement, named — not just the news that something died
tashan doctorover your own config, on your own machine
Start a 7-day trial › Everything measured on this page stays free.