MCP & Integrations

MMW

Last updated 2026-08-22 · benchmark measured 2026-08-22 — deterministic & reproducible

MMW provides governed, persistent memory for AI agents via the MCP protocol.

Is MMW production-ready?

Legit.Show scores MMW 72 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on MMW (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 — 87/100
• Accessibility — 100/100
• Security — 25/100
• Privacy — 25/100
• Reliability — 100/100
• Standards — 92/100
• Discoverability — 77/100

What we measured

• No Content-Security-Policy and no HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 752 ms to first byte.
• Returns a proper 404 for unknown routes.
• 1 of 1 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.
• Discoverable: structured data, canonical URL.

Who it's for

AI agent developers · AI teams · Enterprises needing agent memory management · Infrastructure engineers · Memory-critical AI applications

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