Semantic Memory (holydrug) MCP Server
semantic-memory-mcp
npm
v3.0.4
Source verified
Published by holydrug — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Semantic memory MCP server for Claude Code. Local knowledge graph with vector search — powered by Neo4j.
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 − 13.6 = 86. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −13.6 | Untrusted input concatenated into a command sink ×7 MTC-SRC-009 | injection |
2. Client adoption risk — 86 − 6 = 80. 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 |
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 15
high Shell/command execution in server code (dist/claude.js)MTC-SRC-002
In the server's implementation (`dist/claude.js:7`): 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: rt { spawn } from 'node:child_process'; // --------------------------------------------------------------------------- /
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/claude.js
high Shell/command execution in server code (dist/cli/init-detect.js)MTC-SRC-002
In the server's implementation (`dist/cli/init-detect.js:4`): 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 } from "node:child_process"; /** * Resolve dataDir in priority order: * 1. --data-dir argument (explicit)
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/cli/init-detect.js
high Shell/command execution in server code (dist/cli/start.js)MTC-SRC-002
In the server's implementation (`dist/cli/start.js:1`): 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 } from "node:child_process"; import { existsSync } from "node:fs"; import { join } from "node:path"; import {
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/cli/start.js
high Shell/command execution in server code (dist/cli/status.js)MTC-SRC-002
In the server's implementation (`dist/cli/status.js:4`): 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 } from "node:child_process"; function tryLoadConfig() { // 1. SEMANTIC_MEMORY_CONFIG env var const co
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/cli/status.js
high Shell/command execution in server code (dist/cli/stop.js)MTC-SRC-002
In the server's implementation (`dist/cli/stop.js:1`): 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 } from "node:child_process"; import { existsSync } from "node:fs"; import { join } from "node:path"; import {
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/cli/stop.js
high Shell/command execution in server code (dist/docker.js)MTC-SRC-002
In the server's implementation (`dist/docker.js:1`): 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 } from "node:child_process"; import { existsSync } from "node:fs"; /** * Check if Docker daemon is available
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/docker.js
high Shell/command execution in server code (dist/init-v2-migrate.js)MTC-SRC-002
In the server's implementation (`dist/init-v2-migrate.js:5`): 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 } from "node:child_process"; import { createInterface } from "node:readline/promises"; const __dirname = dirn
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/init-v2-migrate.js
high Shell/command execution in server code (dist/init.js)MTC-SRC-002
In the server's implementation (`dist/init.js:5`): 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 } from "node:child_process"; import { createInterface } from "node:readline/promises"; import { DEFAULT_TRIGG
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/init.js
medium Untrusted input concatenated into a command sink (dist/cli/init-detect.js)MTC-SRC-009
In the server's implementation (`dist/cli/init-detect.js:48`): 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: const output = execSync(`docker compose -f "${composeFile}" ps --format json`, { timeout: 10000, stdio: "pipe"
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/init-detect.js
medium Untrusted input concatenated into a command sink (dist/cli/start.js)MTC-SRC-009
In the server's implementation (`dist/cli/start.js:24`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ..`); try { execSync(`docker compose -f "${composePath}" up -d --wait`, { stdio: ["ignore", "inh
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/cli/start.js
medium Untrusted input concatenated into a command sink (dist/cli/status.js)MTC-SRC-009
In the server's implementation (`dist/cli/status.js:32`): 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: const output = execSync(`docker compose -f "${composePath}" ps --format json`, { encoding: "utf-8", stdio: ["ig
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/status.js
medium Untrusted input concatenated into a command sink (dist/cli/stop.js)MTC-SRC-009
In the server's implementation (`dist/cli/stop.js:22`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ..`); try { execSync(`docker compose -f "${composePath}" down`, { stdio: ["ignore", "inherit", "
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/cli/stop.js
medium Untrusted input concatenated into a command sink (dist/docker.js)MTC-SRC-009
In the server's implementation (`dist/docker.js:41`): 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: const output = execSync(`lsof -i :${port} -sTCP:LISTEN -t 2>/dev/null`, { timeout: 5000,
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/docker.js
medium Untrusted input concatenated into a command sink (dist/init-v2-migrate.js)MTC-SRC-009
In the server's implementation (`dist/init-v2-migrate.js:361`): 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: try { execSync(`docker compose -f ${composePath} up -d`, { timeout: 120000,
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/init-v2-migrate.js
medium Untrusted input concatenated into a command sink (dist/init.js)MTC-SRC-009
In the server's implementation (`dist/init.js:67`): 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: rl) { try { execSync(`curl -sf ${url}/api/tags`, { timeout: 3000, stdio: "pipe" }); return true;
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/init.js
Tools 8
Each tool and what it can reach — statically extracted from the published source.
memory_deleteno sensitive capabilitymemory_graphno sensitive capabilitymemory_ingestno sensitive capabilitymemory_ingest_urlno sensitive capabilitymemory_list_entitiesno sensitive capabilitymemory_searchno sensitive capabilitymemory_storeno sensitive capabilitymemory_validateno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (8 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 |
|---|---|---|---|---|
v3.0.4 latest |
B 80/100 | 15 | 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 semantic-memory-mcp --onlineOther implementations of Semantic Memory 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
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