Is Memory for AI MCP server safe?

Probably. Read the findings first.

C69/100grade C

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

How Memory for AI compares

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

Release history: 2 versions in the registry since 2026-09-12, latest 2026-09-18, typically one every 6 days.

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

3 medium

Code scan3 source files scanned; 4 source files scanned10/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 5 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

mediumnpm install lifecycle script presentinstall.script

package.json: …est": "node --test test/*.test.js", "postinstall": "node install.js" }, "engines": { …

mediumsubprocess with shell=Trueexec.shell-true

memory_for_ai-0.11.0/src/memory_for_ai/_cli.py: …run(args) # noqa: S603 — list form, no shell=True sys.exit(result.returncode) d…

Overall 69/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
not reviewed
Widely used
C
Neo4j Memory
MCP Neo4j Knowledge Graph Memory Server
not reviewed
Established
A
Trace
Code graph MCP: 81 languages, 91 frameworks, 72.7% fewer PR-review tokens, comprehension at parity
not reviewed
Established
A