Cogmemai MCP Server
cogmemai-mcp
npm
v3.23.0
Published by hifriendbot — 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.
CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work is saved even whe
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 − 9.5 = 91. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
2. Client adoption risk — 91 − 7 = 84. 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 6
high Shell/command execution in server code (build/cli.js)MTC-SRC-002
In the server's implementation (`build/cli.js:12`): 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: port { execSync } from 'child_process'; import { readFileSync, writeFileSync, mkdirSync, existsSync, unlinkSync, readdir
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 build/cli.js
high Shell/command execution in server code (build/project.js)MTC-SRC-002
In the server's implementation (`build/project.js:15`): 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: port { execSync } from 'child_process'; import { realpathSync } from 'fs'; const cache = new Map(); export function dete
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 build/project.js
high Shell/command execution in server code (build/tools.js)MTC-SRC-002
In the server's implementation (`build/tools.js:8`): 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: port { execSync } from 'child_process'; import { detectProjectId } from './project.js'; import { FLAG_DIR, VERSION, SESS
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 build/tools.js
medium Hardcoded egress to an external endpoint (build/index.js)MTC-SRC-003
In the server's implementation (`build/index.js:77`): 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: checkForUpdate() { fetch('https://registry.npmjs.org/cogmemai-mcp/latest', { signal: AbortSignal.timeout(50
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 build/index.js
medium Untrusted input concatenated into a command sink (build/cli.js)MTC-SRC-009
In the server's implementation (`build/cli.js:286`): 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(`claude mcp add cogmemai cogmemai-mcp ${envStr} --scope user`, { stdio: 'pipe', timeout
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 build/cli.js
medium Untrusted input concatenated into a command sink (build/tools.js)MTC-SRC-009
In the server's implementation (`build/tools.js:1449`): 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 log = execSync(`git log --oneline ${snapshot.commit.slice(0, 8)}..HEAD`, { enc
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 build/tools.js
Tools 37
Each tool and what it can reach — statically extracted from the published source.
bulk_deleteno sensitive capabilitybulk_updateno sensitive capabilityconsolidate_memoriesno sensitive capabilitydelete_memoryno sensitive capabilitydelete_ruleno sensitive capabilityexport_memoriesno sensitive capabilityextract_memoriesno sensitive capabilityextract_principlesno sensitive capabilityfeedback_memoryno sensitive capabilitygenerate_skillsno sensitive capability
Show 27 more tools ↓
get_analyticsno sensitive capabilityget_file_changesno sensitive capabilityget_memory_linksno sensitive capabilityget_memory_versionsno sensitive capabilityget_project_contextno sensitive capabilityget_stale_memoriesno sensitive capabilityget_tasksno sensitive capabilityget_usageno sensitive capabilityimport_memoriesno sensitive capabilityingest_documentno sensitive capabilitylink_memoriesno sensitive capabilitylist_memoriesno sensitive capabilitylist_rulesno sensitive capabilitylist_tagsno sensitive capabilitylist_trashno sensitive capabilitypreflightno sensitive capabilitypromote_memoryno sensitive capabilityrecall_memoriesno sensitive capabilityrestore_memoryno sensitive capabilitysave_correctionno sensitive capabilitysave_memoryno sensitive capabilitysave_ruleno sensitive capabilitysave_session_summaryno sensitive capabilitysave_taskno sensitive capabilityset_reminderno sensitive capabilityupdate_memoryno sensitive capabilityupdate_taskno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (37 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 3
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 |
|---|---|---|---|---|
v3.23.0 latest |
B 84/100 | 6 | 1.13.0 | 2026-09-07 |
v3.21.1 |
B 84/100 | 6 | 1.12.1 | 2026-08-16 |
v3.21.0 |
B 84/100 | 6 | 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 cogmemai-mcp --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