Mneme Ai (patsa2561-art) MCP Server
mneme-ai
npm
v3.153.0
Published by patsa2561-art — 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.
Mneme — the memory layer for your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.
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 − 15.4 = 85. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −14.2 | Untrusted input concatenated into a command sink ×8 MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 85 − 7 = 78. 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 19
high Shell/command execution in server code (bin/postinstall-mneme-lite.cjs)MTC-SRC-002
In the server's implementation (`bin/postinstall-mneme-lite.cjs:42`): 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: nSync } = require("node:child_process"); const here = __dirname; const mnemeRoot = path.resolve(here, ".."); // ──────
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/postinstall-mneme-lite.cjs
high Shell/command execution in server code (bin/preinstall-mneme.cjs)MTC-SRC-002
In the server's implementation (`bin/preinstall-mneme.cjs:69`): 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: nSync } = require("node:child_process"); const crypto = require("node:crypto"); const IS_WIN = process.platform === "wi
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/preinstall-mneme.cjs
high Shell/command execution in server code (dist/autonomic_breath_hook.js)MTC-SRC-002
In the server's implementation (`dist/autonomic_breath_hook.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: rt { spawn } from "node:child_process"; import { join } from "node:path"; import { autonomicBreath, git } from "@mneme-a
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/autonomic_breath_hook.js
high Shell/command execution in server code (dist/commands/accountability.js)MTC-SRC-002
In the server's implementation (`dist/commands/accountability.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, readFileSync, writeFileSync, mkdirSync } from "node:fs"; im
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/commands/accountability.js
high Shell/command execution in server code (dist/commands/attest.js)MTC-SRC-002
In the server's implementation (`dist/commands/attest.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, mkdirSync, readFileSync, appendFileSync, writeFileSync, chm
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/commands/attest.js
high Shell/command execution in server code (dist/commands/audit.js)MTC-SRC-002
In the server's implementation (`dist/commands/audit.js:17`): 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: ecFileSync } from "node:child_process"; import { writeFileSync } from "node:fs"; import kleur from "kleur"; import { aud
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/commands/audit.js
high Shell/command execution in server code (dist/commands/boot.js)MTC-SRC-002
In the server's implementation (`dist/commands/boot.js:50`): 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: void import("node:child_process").then(({ spawn }) => { try { spawn(process.execPath,
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/commands/boot.js
high Shell/command execution in server code (dist/commands/bot.js)MTC-SRC-002
In the server's implementation (`dist/commands/bot.js:17`): 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: ecFileSync } from "node:child_process"; import kleur from "kleur"; import { bot, git } from "@mneme-ai/core"; import { u
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/commands/bot.js
medium Untrusted input concatenated into a command sink (dist/commands/accountability.js)MTC-SRC-009
In the server's implementation (`dist/commands/accountability.js:8`): 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: cwd) { try { return execSync(`git ${args}`, { cwd, encoding: "utf8", stdio: ["ignore", "pipe", "ignore"] }).trim();
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/commands/accountability.js
medium Untrusted input concatenated into a command sink (dist/commands/attest.js)MTC-SRC-009
In the server's implementation (`dist/commands/attest.js:12`): 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 { return execSync(`git ${args}`, { cwd, encoding: "utf8", stdio: ["ignore", "pipe", "ignore"] }).trim();
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/commands/attest.js
medium Untrusted input concatenated into a command sink (dist/commands/index-super.js)MTC-SRC-009
In the server's implementation (`dist/commands/index-super.js:66`): 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: D"; const out = execSync(`git log ${range} --format=%H`, { cwd, encoding: "utf8", timeout: 30_000, stdio: ["igno
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/commands/index-super.js
medium Untrusted input concatenated into a command sink (dist/commands/outliers.js)MTC-SRC-009
In the server's implementation (`dist/commands/outliers.js:115`): 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 json = execSync(`npm view ${pkg} time deprecated maintainers --json`, { encoding: "utf8", stdio: ["igno
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/commands/outliers.js
medium Untrusted input concatenated into a command sink (dist/commands/reckon.js)MTC-SRC-009
In the server's implementation (`dist/commands/reckon.js:7`): 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: cwd) { try { return execSync(`git ${args.join(" ")}`, { cwd, encoding: "utf8", stdio: ["ignore", "pipe", "ignore"] }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/commands/reckon.js
medium Untrusted input concatenated into a command sink (dist/commands/setup-free.js)MTC-SRC-009
In the server's implementation (`dist/commands/setup-free.js:126`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ere" : "which"; execSync(`${checker} ${cmd}`, { stdio: "ignore" }); return true; } catch {
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/commands/setup-free.js
medium Untrusted input concatenated into a command sink (dist/commands/warm.js)MTC-SRC-009
In the server's implementation (`dist/commands/warm.js:7`): 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: cwd) { try { return execSync(`git ${args.join(" ")}`, { cwd, encoding: "utf8", stdio: ["ignore", "pipe", "ignore"] }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/commands/warm.js
medium Untrusted input concatenated into a command sink (dist/utils/args.js)MTC-SRC-009
In the server's implementation (`dist/utils/args.js:55`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: y { const out = execSync(`git rev-parse --verify "${ref}^{commit}"`, { cwd, stdio: ["ign
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/utils/args.js
low Shell/command execution in packaging/dev tooling (dist/commands/black-sheep.smoke.test.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/commands/black-sheep.smoke.test.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: spawnSync } from "node:child_process"; import { existsSync, mkdtempSync, rmSync, statSync, writeFileSync, readFileSync
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/commands/black-sheep.smoke.test.js
low Shell/command execution in packaging/dev tooling (dist/commands/bot.smoke.test.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/commands/bot.smoke.test.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: spawnSync } from "node:child_process"; import { existsSync } from "node:fs"; import { join } from "node:path"; const RE
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/commands/bot.smoke.test.js
low Package runs install-time scripts (preinstall, postinstall)MTC-SUP-010
"mneme-ai" executes preinstall/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 -e "try{const fs=require('node:fs');const path=require('node:path');const os=require('node:os');const{spawnSync}=require('node:child_process');const crypto
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package mneme-ai
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 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 |
|---|---|---|---|---|
v3.153.0 latest |
C 78/100 | 19 | 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 mneme-ai --onlineOther implementations of Mneme Ai 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Analytics & Monitoring
Public-safe MCP admin discovery contract descriptors and response builders.
Pokemon Champions battle advisor MCP server
Airflow MCP server — DAG list, runs, task instances, log tails, trigger and clear over the Airflow REST API
MCP analytics wrapper SDK that instruments MCP tool declarations with telemetry.
AI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.
AI-native social listening. Monitor buying signals and run GTM workflows via natural language.