Robrain MCP Server
robrain
npm
v2.4.9
Published by adelinamart — 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.
RoBrain CLI for installation, setup, and memory workflows
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 14
high Shell/command execution in server code (dist/commands/explain.js)MTC-SRC-002
In the server's implementation (`dist/commands/explain.js:20`): 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'; export async function explainCommand(filePath, opts) { console.log(); 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/commands/explain.js
high Shell/command execution in server code (dist/commands/inject.js)MTC-SRC-002
In the server's implementation (`dist/commands/inject.js:18`): 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'; export async function injectCommand(opts) { console.log(); const config
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/inject.js
high Shell/command execution in server code (dist/commands/mcp.js)MTC-SRC-002
In the server's implementation (`dist/commands/mcp.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: import { spawn } from 'child_process'; import chalk from 'chalk'; import { readConfig } from '../lib/config.js'; 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/commands/mcp.js
high Shell/command execution in server code (dist/commands/outcomes.js)MTC-SRC-002
In the server's implementation (`dist/commands/outcomes.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: { execFileSync } from 'child_process'; import { cwd } from 'process'; import { readConfig, isAuthenticated, isCloudInst
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/outcomes.js
high Shell/command execution in server code (dist/commands/synth.js)MTC-SRC-002
In the server's implementation (`dist/commands/synth.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: import { spawn } from 'child_process'; import { existsSync } from 'fs'; import { dirname, join } from '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/commands/synth.js
high Shell/command execution in server code (dist/commands/up.js)MTC-SRC-002
In the server's implementation (`dist/commands/up.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: Sync, spawnSync } from 'child_process'; import { randomBytes } from 'crypto'; import { existsSync, mkdirSync, readFileSy
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/up.js
high Shell/command execution in server code (dist/lib/editor.js)MTC-SRC-002
In the server's implementation (`dist/lib/editor.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 { existsSync, readFileSync, writeFileSync, mkdirSync } from 'fs'; 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/lib/editor.js
high Shell/command execution in server code (dist/lib/project.js)MTC-SRC-002
In the server's implementation (`dist/lib/project.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: port { execSync } from 'child_process'; import { createHash } from 'crypto'; /** Derive a stable project ID from the wor
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/lib/project.js
medium Hardcoded egress to an external endpoint (dist/lib/project.js)MTC-SRC-003
In the server's implementation (`dist/lib/project.js:137`): 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: const resp = await fetch('https://api.anthropic.com/v1/messages', { method: 'POST', headers
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/lib/project.js
low Hardcoded egress to an external endpoint in packaging/dev tooling (scripts/verify-release-artifacts.mjs)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify-release-artifacts.mjs:47`): 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: const tokenRes = await fetch(`https://ghcr.io/token?scope=repository:${ghcrRepo}:pull`) const { token } = await token
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 scripts/verify-release-artifacts.mjs
low Shell/command execution in packaging/dev tooling (scripts/verify-publish-tarball.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify-publish-tarball.mjs: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: FileSync, spawn } from 'child_process' import { existsSync, mkdirSync, readFileSync, rmSync } from 'fs' import { tmpdir
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 scripts/verify-publish-tarball.mjs
low Shell/command execution in packaging/dev tooling (scripts/verify-release-artifacts.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify-release-artifacts.mjs: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: { execFileSync } from 'child_process' import { readFileSync } from 'fs' import { dirname, join } from 'path' import { f
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 scripts/verify-release-artifacts.mjs
low Dynamic module load from a non-literal in packaging/dev tooling (scripts/verify-publish-tarball.mjs)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify-publish-tarball.mjs:48`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: SensingMcpDir } = await import(bundleUrl) const dir = resolveInstalledSensingMcpDir() if (!dir) fail('resolveInstall
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 scripts/verify-publish-tarball.mjs
low Package runs install-time scripts (postinstall)MTC-SUP-010
"robrain" 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: node scripts/chmod-bin.cjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package robrain
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 7
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 |
|---|---|---|---|---|
v2.4.9 latest |
A 92/100 | 14 | 1.13.0 | 2026-09-07 |
v2.4.8 |
A 92/100 | 14 | 1.12.1 | 2026-08-04 |
v2.4.7 |
A 92/100 | 14 | 1.12.1 | 2026-07-28 |
v2.4.5 |
A 92/100 | 13 | 1.10.0 | 2026-07-25 |
v2.4.4 |
B 87/100 | 13 | 1.8.0 | 2026-07-23 |
Show 2 more versions ↓
v2.4.3 |
B 87/100 | 13 | 1.8.0 | 2026-07-23 |
v2.4.0 |
A 94/100 | 13 | 1.5.0 | 2026-07-22 |
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 robrain --onlineMore in Databases
Security scan results for the A5sql MCP server.
Expose AgentsKit tools as an MCP server — use them from Claude Desktop, Cursor, Windsurf, or any MCP host.
MCP server for Aiven cloud data platform - manage PostgreSQL, Kafka, and other services
MCP Server for All-Inkl.com hosting via KAS API
Structured aquarium, marine, terrarium and paludarium data for AI agents.
MCP server that gives your AI agent real vehicle data — specs, representative images, federal recalls, owner complaints, service bulletins, defect investigations, and OBD-II DTC reference — from the CarVector API.