Brain (samleeney) MCP Server
brain-mcp
npm
v2.2.0
Published by samleeney — 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.
Brain MCP Server - Semantic knowledge base access for Claude Code via Model Context Protocol. Provides intelligent search and navigation of files from multiple locations through native MCP tools.
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 − 11 = 89. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11 | Untrusted input concatenated into a command sink ×3 MTC-SRC-009 | injection |
2. Client adoption risk — 89 − 7 = 82. 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 8
high Shell/command execution in server code (dist/cli/brain.js)MTC-SRC-002
In the server's implementation (`dist/cli/brain.js:183`): 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 } = require('child_process'); textContent = execSync(`pdftotext -layout "${filePath}" -`, {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/brain.js
high Shell/command execution in server code (dist/cli/brainV2.js)MTC-SRC-002
In the server's implementation (`dist/cli/brainV2.js:183`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execSync } = require('child_process'); textContent = execSync(`pdftotext -layout "${filePath}" -`, {
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/brainV2.js
high Shell/command execution in server code (dist/mcp/server.js)MTC-SRC-002
In the server's implementation (`dist/mcp/server.js:194`): 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: > __importStar(require('child_process'))); content = execSync(`pdftotext -layout "${fileRecord.a
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/mcp/server.js
high Shell/command execution in server code (dist/parser/PDFParser.js)MTC-SRC-002
In the server's implementation (`dist/parser/PDFParser.js:45`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: r(require("fs")); const child_process_1 = require("child_process"); const pdf_parse_1 = __importDefault(require("pdf-par
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/parser/PDFParser.js
medium Untrusted input concatenated into a command sink (dist/cli/brain.js)MTC-SRC-009
In the server's implementation (`dist/cli/brain.js:184`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: textContent = execSync(`pdftotext -layout "${filePath}" -`, { encoding: 'utf-8',
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/brain.js
medium Untrusted input concatenated into a command sink (dist/cli/brainV2.js)MTC-SRC-009
In the server's implementation (`dist/cli/brainV2.js:184`): 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: textContent = execSync(`pdftotext -layout "${filePath}" -`, { encoding: 'utf-8',
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/brainV2.js
medium Untrusted input concatenated into a command sink (dist/mcp/server.js)MTC-SRC-009
In the server's implementation (`dist/mcp/server.js:195`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: content = execSync(`pdftotext -layout "${fileRecord.absolutePath}" -`, { encod
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/mcp/server.js
medium Dynamic module load from a non-literal (dist/cli/brain.js)MTC-SRC-005
In the server's implementation (`dist/cli/brain.js:317`): 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: const { setupBrain } = require(setupPath); await setupBrain(); } catch (error) { console.error(
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/brain.js
Tools 5
Each tool and what it can reach — statically extracted from the published source.
brain_listno sensitive capabilitybrain_overviewno sensitive capabilitybrain_readno sensitive capabilitybrain_researchno sensitive capabilitybrain_searchno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (5 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 |
|---|---|---|---|---|
v2.2.0 latest |
B 82/100 | 8 | 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 brain-mcp --onlineOther implementations of Brain 4
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
Any model, one interface — the three.ws multi-provider LLM router over MCP. Discover available providers/models (Claude, GPT-4o, Qwen, DeepSeek, NVIDIA Nemotron, IBM Granite…) and run a chat completion through whichever one fits. Free tiers need no key; p
SHELET-compliant cognitive prosthetic for AI agents — 25 stratified MCP skills with structural citation discipline
MCP server providing long-term memory for AI agents with semantic, graph, and temporal retrieval. Works with Claude Desktop, Claude Code, and Cursor.
Personal Knowledge Brain for developers — MCP server with typed neurons, hybrid search (FTS5 + vector), knowledge graph, vault encryption, time-travel history, and spaced repetition. 100% local, SQLite-based.
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