Brain (mordechaipotash) MCP Server
brain-mcp
PyPI
v0.4.1
Published by mordechaipotash — 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.
SHELET-compliant cognitive prosthetic for AI agents — 25 stratified MCP skills with structural citation discipline
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. 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 3
high Shell/command execution in server code (brain_mcp/cli.py)MTC-SRC-002
In the server's implementation (`brain_mcp/cli.py:515`): 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: result = subprocess.run( [sys.executable, "-m", "pip", "install", "fastembed>=0.5
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 brain_mcp/cli.py
high Shell/command execution in server code (brain_mcp/dashboard/routes/settings.py)MTC-SRC-002
In the server's implementation (`brain_mcp/dashboard/routes/settings.py:267`): 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: try: result = subprocess.run( ["crontab", "-l"], capture_output=True, text=True, timeout=5
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 brain_mcp/dashboard/routes/settings.py
low Dynamic code execution in packaging/dev tooling (brain_mcp/dashboard/static/htmx.min.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`brain_mcp/dashboard/static/htmx.min.js:1`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .body,function(){return eval(e)})}function j(t){const e=Q.on("htmx:load",function(e){t(e.detail.elt)});return e}function
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 brain_mcp/dashboard/static/htmx.min.js
Tools 25
Each tool and what it can reach — statically extracted from the published source.
alignment_checkno sensitive capabilitybrain_statsno sensitive capabilitycognitive_patternsno sensitive capabilitycontext_recoveryno sensitive capabilityconversations_by_dateno sensitive capabilitydormant_contextsno sensitive capabilityget_conversationno sensitive capabilityget_principleno sensitive capabilitygithub_searchno sensitive capabilitylist_principlesno sensitive capability
Show 15 more tools ↓
open_threadsno sensitive capabilityquery_analyticsno sensitive capabilitysearch_conversationsno sensitive capabilitysearch_docsno sensitive capabilitysearch_summariesno sensitive capabilitysemantic_searchno sensitive capabilityswitching_costno sensitive capabilitythinking_trajectoryno sensitive capabilitytrust_dashboardno sensitive capabilitytunnel_historyno sensitive capabilitytunnel_stateno sensitive capabilityunfinished_threadsno sensitive capabilityunified_searchno sensitive capabilitywhat_do_i_thinkno sensitive capabilitywhat_was_i_thinkingno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (25 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 2
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 |
|---|---|---|---|---|
v0.4.1 latest |
A 93/100 | 3 | 1.13.0 | 2026-08-25 |
v0.4.0 |
A 93/100 | 3 | 1.12.1 | 2026-07-27 |
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 --online --registry pypiOther 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
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.
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.
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