Mmcp.market

Head to head

Phi Guard vs Maginary

Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.

Phi Guardio.github.Abidit/phi-guard-mcp
A
No reviews yet

Local-first PHI detection for source code, LLM prompts, logs, and analytics

Full listing
Maginaryio.github.maginaryai/maginary-mcp
B
No reviews yet

AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.

Full listing

The short version

Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. The safety scan favours Phi Guard (92/100 against 83). Maginary is hosted and callable through the gateway; Phi Guard runs on your own machine.

 Phi GuardMaginary
User ratingNo reviews yetNo reviews yet
Safety gradeA92/100B83/100
AdoptionGrowingGrowing
GitHub stars01
Downloads / week901.2k
Runs whereYour machine (local)Hosted (remote)
Gateway-readyNoYes
Tools216
Write actions—6
Price per callFreeFree
LicenceMITMIT
Last release2026-09-182026-09-15
CategoryAI and agentsAI and agents

Other comparisons

Phi Guard vs Agent-Native AnalyticsPhi Guard vs HOL GuardPhi Guard vs prompt-protectionPhi Guard vs mcpmPhi Guard vs haiku.ragAll AI and agents servers