Is remem-mcp — Local-first MCP Memory + CodeGraph + Wiki MCP server safe?
Yes, with the usual care.
Safe to use. Minor gaps such as a missing repository or slower maintenance.
No critical or high findings in the latest scan.
How remem-mcp — Local-first MCP Memory + CodeGraph + Wiki compares
Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 77/100
- higher than 40% of 802 Databases servers
- Tools that change things
- 18%
- typical: 7%. Fewer write tools means less an agent can break
What its tools let an agent do: 23 read · 5 change
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
2 medium
- Code scan6 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 qualitylocal package, no credentials required12/15
- Maintenancelast push 3 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (2)
- mediumnpm install lifecycle script present
install.script - mediumnpm install lifecycle script present
install.scriptpackage.json: … "start": "node dist/index.js", "postinstall": "node scripts/postinstall.js", "pre…
Overall 77/100. 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 remem-mcp — Local-first MCP Memory + CodeGraph + Wiki does
- RememLocal-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.not reviewedEstablishedB
- MycTask queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.not reviewedEstablishedC
- CPersonaPersistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.not reviewedGrowingA
remem-mcp — Local-first MCP Memory + CodeGraph + Wiki reviews, tools and install