Context7 vs MDN MCP (experimental)
Both are up-to-date docs for coding MCP servers, and we ran both through the same test (docs fact, library lookup, mdn docs fact) in each app. Context7 passed 4 of 4 apps we tested it in; MDN MCP (experimental) passed 3 of 3.
Test results side by side
| Context7 | MDN MCP (experimental) | |
|---|---|---|
| Claude Code | Passed 2026-10-20 | Passed 2026-10-23 |
| Cursor | Passed 2026-10-20 | Passed 2026-10-23 |
| Claude Desktop | Passed 2026-10-18 | Not tested yet |
| ChatGPT (Codex) | Passed 2026-10-15 | Passed 2026-10-23 |
| Tools exposed (protocol check) | 2 tools | 3 tools |
| GitHub stars | 63,050 | 192 |
| License | MIT | MPL-2.0 |
| Last push | 2026-10-14 | 2026-10-21 |
Results from our own harness runs, dated per cell. Stars and last push from GitHub at our last data refresh. We don’t pick a winner here: which one fits depends on your app and setup.
What each does
Context7: Pulls current, version-specific library docs into the agent's context so code suggestions match the real API.
MDN MCP (experimental): MDN's experimental server for searching MDN docs and browser-compatibility data, so coding agents use current web platform facts. MDN says it logs queries while it's an experiment.
