Cosmos (Polarity) MCP Server
@polarity-lab/cosmos-mcp
npm
v0.9.36
Published by @polarity-lab — 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.
Read and write a personal knowledge graph, the Polarity exocortex, from any LLM client.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. 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 12
high Shell/command execution in server code (bin/cosmos-mcp.js)MTC-SRC-002
In the server's implementation (`bin/cosmos-mcp.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 { createRequire } from "node:module"; import { existsSync, mkdirSync, wri
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/cosmos-mcp.js
high Shell/command execution in server code (dist/auth/bootstrap.js)MTC-SRC-002
In the server's implementation (`dist/auth/bootstrap.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: { execFile } from "node:child_process"; import { TOKEN_PATHS } from "../config.js"; const DEFAULT_COSMOS_URL = process.e
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/auth/bootstrap.js
high Shell/command execution in server code (dist/daemon/cli.js)MTC-SRC-002
In the server's implementation (`dist/daemon/cli.js:9`): 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 { loadSyncConfig } from "./config.js"; import { applyDaemonConfig, getDae
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/daemon/cli.js
high Shell/command execution in server code (dist/daemon/manage.js)MTC-SRC-002
In the server's implementation (`dist/daemon/manage.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: spawnSync } from "node:child_process"; import { chmodSync, existsSync, mkdirSync, writeFileSync } from "node:fs"; impor
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/daemon/manage.js
high Shell/command execution in server code (dist/daemon/menu-cli.js)MTC-SRC-002
In the server's implementation (`dist/daemon/menu-cli.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: spawnSync } from "node:child_process"; import { chmodSync, existsSync, mkdirSync, writeFileSync } from "node:fs"; impor
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/daemon/menu-cli.js
high Shell/command execution in server code (dist/daemon/paths.js)MTC-SRC-002
In the server's implementation (`dist/daemon/paths.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: ecFileSync } from "node:child_process"; import { existsSync } from "node:fs"; import { homedir } from "node:os"; 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/daemon/paths.js
high Shell/command execution in server code (dist/settings/cli.js)MTC-SRC-002
In the server's implementation (`dist/settings/cli.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: rt { spawn } from "node:child_process"; import { execFileSync } from "node:child_process"; import { existsSync } from "n
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/settings/cli.js
high Shell/command execution in server code (dist/settings/server.js)MTC-SRC-002
In the server's implementation (`dist/settings/server.js:6`): 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: ync, spawn } from "node:child_process"; import { dirname, join } from "node:path"; import { fileURLToPath } from "node: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/settings/server.js
high Shell/command execution in server code (dist/settings/sync-jobs.js)MTC-SRC-002
In the server's implementation (`dist/settings/sync-jobs.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: rt { spawn } from "node:child_process"; import { existsSync } from "node:fs"; import { dirname, join } from "node:path";
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/settings/sync-jobs.js
high Shell/command execution in server code (dist/sources/imessage/caption.js)MTC-SRC-002
In the server's implementation (`dist/sources/imessage/caption.js:19`): 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 path from "node:path"; import os from "node:os"; // Skip files larger tha
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/sources/imessage/caption.js
medium Hardcoded egress to an external endpoint (dist/stack/polarity-stack.crosslinks.js)MTC-SRC-003
In the server's implementation (`dist/stack/polarity-stack.crosslinks.js:12`): 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: _mcp(body) { return fetch('https://cosmos.polarity-lab.com/api/mcp', { method: 'POST', headers: { 'C
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/stack/polarity-stack.crosslinks.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@polarity-lab/cosmos-mcp" 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: npm rebuild better-sqlite3 2>/dev/null || true
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @polarity-lab/cosmos-mcp
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 |
|---|---|---|---|---|
v0.9.36 latest |
A 92/100 | 12 | 1.13.0 | 2026-08-25 |
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 @polarity-lab/cosmos-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