Local Memory (vheins) MCP Server
@vheins/local-memory-mcp
npm
v0.44.1
Published by @vheins — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Local memory service for coding copilot agents.
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. 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 |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 4
high Shell/command execution in server code (bin/ensure-dashboard-build.mjs)MTC-SRC-002
In the server's implementation (`bin/ensure-dashboard-build.mjs:25`): 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: spawnSync } from "node:child_process"; const REPO_ROOT = resolve(dirname(fileURLToPath(import.meta.url)), ".."); 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/ensure-dashboard-build.mjs
high Shell/command execution in server code (dist/chunk-C5HOOLO3.js)MTC-SRC-002
In the server's implementation (`dist/chunk-C5HOOLO3.js:2131`): 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: result.changes }; } exec(sql) { this.db.exec(sql); } all(sql, params = []) { const stmt = this.prepare(s
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 dist/chunk-C5HOOLO3.js
low Hardcoded egress to an external endpoint in packaging/dev tooling (dist/dashboard/public/assets/index-CZ6bL1di.js)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/dashboard/public/assets/index-CZ6bL1di.js:130`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ion f(){try{let e=await fetch(`https://api.npmjs.org/downloads/point/last-month/@vheins/local-memory-mcp`);if(e.ok){let
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 dist/dashboard/public/assets/index-CZ6bL1di.js
low Dynamic code execution in packaging/dev tooling (dist/dashboard/public/assets/index-CZ6bL1di.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/dashboard/public/assets/index-CZ6bL1di.js:61`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: (`value`);!n||!r||(t[n]=Function(`return ${r}`)())}),t},Lr=e=>{let t={};return Array.from(e.querySelectorAll(`swal-butto
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 dist/dashboard/public/assets/index-CZ6bL1di.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 10
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 |
|---|---|---|---|---|
v0.44.1 latest |
A 93/100 | 4 | 1.13.0 | 2026-09-07 |
v0.44.0 |
A 93/100 | 4 | 1.13.0 | 2026-09-06 |
v0.43.2 |
A 93/100 | 4 | 1.13.0 | 2026-09-04 |
v0.43.1 |
A 93/100 | 4 | 1.13.0 | 2026-08-29 |
v0.41.1 |
A 93/100 | 4 | 1.13.0 | 2026-08-25 |
Show 5 more versions ↓
v0.41.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-18 |
v0.40.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-17 |
v0.39.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-15 |
v0.38.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-14 |
v0.37.0 |
A 93/100 | 4 | 1.12.1 | 2026-08-12 |
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 @vheins/local-memory-mcp --onlineOther implementations of Local Memory 5
Independent packages implementing the same tool, scanned with the same engine. Compare all 6 side by side →
Persistent local memory for any MCP client. SQLite + FTS5 + sqlite-vec hybrid retrieval, bi-temporal asOf queries, contradiction detection, LLM-free reflection. Multilingual embeddings. Knowledge Graph. No cloud, no API keys.
Lightweight memory server with SQLite-based vector search and context tagging.
Structured agent memory with SQLite/FTS5 + optional Qdrant vector search, exposed via MCP
Local memory server for AI agents using SQLite and MCP
Local Memory MCP Server - AI-powered persistent memory system for Claude Code, Claude Desktop, Gemini, Codex, OpenCode and other MCP-compatible tools
More 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