MCP & Integrations

Kivgraph

Last updated 2026-08-31 · benchmark measured 2026-08-31 — deterministic & reproducible

Kivgraph is a local MCP server that gives AI coding agents cross-repository code intelligence.

Is Kivgraph production-ready?

Legit.Show scores Kivgraph 70 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Kivgraph (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 78/100
• Accessibility — 100/100
• Security — 25/100
• Privacy — 0/100
• Reliability — 100/100
• Standards — 100/100
• Discoverability — 90/100

What we measured

• No Content-Security-Policy and no HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 385 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.
• Discoverable: structured data, OpenGraph image, canonical URL.

Who it's for

AI coding agents · Software engineers · DevOps teams · Code maintainers · TypeScript/Go developers

Visit Kivgraph → · Alternatives to Kivgraph → · How this was measured →