Claude Persistent Memory MCP Server
@alex900530/claude-persistent-memory
npm
v1.1.1
Published by @alex900530 — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Persistent memory system for Claude Code — hybrid BM25 + vector search, LLM-driven structuring, automatic clustering
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 7.5 = 93. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 93 − 8 = 85. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 8
high Shell/command execution in server code (bin/uninstall.js)MTC-SRC-002
In the server's implementation (`bin/uninstall.js:31`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { require('child_process').execSync(`launchctl unload ${plist}`, { stdio: 'ignore' }); } catch {} f
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/uninstall.js
high Shell/command execution in server code (hooks/pre-compact-hook.js)MTC-SRC-002
In the server's implementation (`hooks/pre-compact-hook.js:10`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: st { spawn } = require('child_process'); const path = require('path'); const fs = require('fs'); const config = require
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server hooks/pre-compact-hook.js
high Shell/command execution in server code (lib/memory-db.js)MTC-SRC-002
In the server's implementation (`lib/memory-db.js:16`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execSync } = require('child_process'); // ============== Configuration ============== const config = require('../con
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server lib/memory-db.js
medium Untrusted input concatenated into a command sink (bin/uninstall.js)MTC-SRC-009
In the server's implementation (`bin/uninstall.js:31`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: equire('child_process').execSync(`launchctl unload ${plist}`, { stdio: 'ignore' }); } catch {} fs.unlinkSync(pli
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/uninstall.js
medium Dynamic module load from a non-literal (config.js)MTC-SRC-005
In the server's implementation (`config.js:4`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: )) { module.exports = require(configPath); } else { module.exports = require('./config.default'); }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server config.js
low Shell/command execution in packaging/dev tooling (bin/setup.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`bin/setup.js:334`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { require('child_process').execSync(`launchctl unload ${plistPath} 2>/dev/null`, { stdio: 'ignore' });
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/setup.js
low Dynamic module load from a non-literal in packaging/dev tooling (bin/setup.js)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`bin/setup.js:204`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; const mod = await import(transformersPath); const pipeline = mod.pipeline || mod.default?.pipeline; const
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/setup.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@alex900530/claude-persistent-memory" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node bin/setup.js --postinstall
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @alex900530/claude-persistent-memory
Tools 4
Each tool and what it can reach — statically extracted from the published source.
memory_saveno sensitive capabilitymemory_searchno sensitive capabilitymemory_statsno sensitive capabilitymemory_validateno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (4 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.1.1 latest |
B 85/100 | 8 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @alex900530/claude-persistent-memory --onlineMore in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology