@modelcontextprotocol/sdk
npm package · declared by 143 of 2,343 sampled repositories · graph computed 2026-08-24
Counted from the runtime dependencies public repositories declare — not the resolved tree. A transitive dependency is a consequence; a declared one is a choice. Development dependencies are excluded because they repeat across every project in a language regardless of what is being built.
Declared with
ranked by association, not by count| Declared with | Repositories | vs chance |
|---|---|---|
| zod | 77 of 2,343 | 0.58 |
| better-sqlite3 | 18 of 2,343 | 0.42 |
| hono | 8 of 2,343 | 0.40 |
| @anthropic-ai/sdk | 10 of 2,343 | 0.39 |
| @clack/prompts | 9 of 2,343 | 0.38 |
| ws | 19 of 2,343 | 0.37 |
| express | 20 of 2,343 | 0.36 |
| commander | 21 of 2,343 | 0.36 |
| yaml | 13 of 2,343 | 0.34 |
| undici | 11 of 2,343 | 0.34 |
| dotenv | 22 of 2,343 | 0.33 |
| chalk | 13 of 2,343 | 0.30 |
| openai | 12 of 2,343 | 0.30 |
| axios | 13 of 2,343 | 0.21 |
| uuid | 8 of 2,343 | 0.19 |
| react | 19 of 2,343 | 0.02 |
| react-dom | 10 of 2,343 | -0.09 |
Every pair above is counted from the same evidence: repo manifest.
Used instead
candidates · shares a neighbourhood and refuses to co-occurNo alternative measured. A pair qualifies only if it shares a neighbourhood and then fails to appear together against an expectation that it would — and almost everything that shares a neighbourhood does appear together. That is the test working, not a gap in the data: similarity alone would list this tool’s closest neighbours as alternatives, and most of them are things it is used with.