Is AI Agent Firewall MCP server safe?

Probably. Read the findings first.

C58/100grade C

Use with care. Some checks failed or could not be verified.

How AI Agent Firewall compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 58/100; higher than 15% of 4,460 AI and agents servers
Tools that change things: 8%; typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 11 read · 1 create

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

2 medium

Code scan40 source files scanned15/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitystatic API keys via environment variables6/15
Maintenancelast push 51 days ago12/15
Maintainer identitynamespace and repository owner differ; GitHub account older than a year5/10

mediumnpm install lifecycle script presentinstall.script

package.json: …-noEmit", "test": "vitest run", "postinstall": "node -e \"try{require('fs').accessSync…

Overall 58/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

three.ws Provenance
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
More from nirholas →
not reviewed
Established
B
Claude Real Video
Let any LLM watch a video locally — and search everything it has ever watched.
not reviewed
Established
A
Decionis
Authorize consequential AI agent actions before execution
not reviewed
Established
A