Is Memory MCP server safe?
Probably. Read the findings first.
Use with care. Some checks failed or could not be verified.
What to know before installing
- highShell command built from a string (injection risk)
How Memory compares
Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 57/100
- higher than 11% of 1,119 Developer tools servers
- Tools that change things
- 10%
- typical: 5%. Fewer write tools means less an agent can break
What its tools let an agent do: 9 read · 1 change
Public scan report
scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it
1 high
- Code scan19 source files scanned13/25
- –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 242 days ago4/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- highShell command built from a string (injection risk)
exec.shell-concatdist/cli.js: …= require("child_process"); exec(`open "${outputPath}"`); } return…
Overall 57/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Other servers that do what Memory does
- PalinodeInspectable, correctable project memory in git-versioned Markdown for AI agents.not reviewedEstablishedC
- KindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.not reviewedEstablishedA
- KindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.not reviewedEstablishedB