Neurostack (raphasouthall) MCP Server
neurostack
PyPI
v0.16.0
Published by raphasouthall — 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.
Build, maintain, and search your knowledge vault. CLI + MCP server with stale note detection, semantic search, and neuroscience-grounded memory.
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 13
high Shell/command execution in server code (npm/bin/neurostack.js)MTC-SRC-002
In the server's implementation (`npm/bin/neurostack.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: , execSync } = require("child_process"); const fs = require("fs"); const path = require("path"); const os = require("os"
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 npm/bin/neurostack.js
high Shell/command execution in server code (src/neurostack/brief.py)MTC-SRC-002
In the server's implementation (`src/neurostack/brief.py:56`): 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( ["git", "log", f"--max-count={limit}", "--oneline", "--no-decorate"]
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 src/neurostack/brief.py
high Shell/command execution in server code (src/neurostack/cli/sessions.py)MTC-SRC-002
In the server's implementation (`src/neurostack/cli/sessions.py:250`): 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: rs.target """ ) subprocess.run( ["systemctl", "--user", "daemon-reload"], check=False, capture_o
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 src/neurostack/cli/sessions.py
high Shell/command execution in server code (src/neurostack/cli/setup.py)MTC-SRC-002
In the server's implementation (`src/neurostack/cli/setup.py:33`): 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: y: result = subprocess.run( [nvidia_smi, "--query-gpu=name,memory.total", "
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 src/neurostack/cli/setup.py
high Shell/command execution in server code (src/neurostack/cli/utils.py)MTC-SRC-002
In the server's implementation (`src/neurostack/cli/utils.py:49`): 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( [fuser, db_path], capture_output=True, text=True, timeou
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 src/neurostack/cli/utils.py
high Shell/command execution in server code (src/neurostack/tools/file_tools.py)MTC-SRC-002
In the server's implementation (`src/neurostack/tools/file_tools.py:159`): 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: etedProcess: return subprocess.run( ["git", *args], cwd=str(cwd), check=check, capture_output=True,
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 src/neurostack/tools/file_tools.py
medium Tool "vault_write_file" can modify the filesystemMTC-CAP-002
Tool "vault_write_file" can write, overwrite or delete files (keyword "write_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool vault_write_file
medium Tool "vault_delete_file" can modify the filesystemMTC-CAP-002
Tool "vault_delete_file" can write, overwrite or delete files (keyword "delete_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool vault_delete_file
medium Dynamic module load from a non-literal (npm/bin/neurostack.js)MTC-SRC-005
In the server's implementation (`npm/bin/neurostack.js:29`): 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: nc(preuninstall)) { require(preuninstall); } console.log(" \x1b[36m▸\x1b[0m Removing npm package...\n"); try
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 npm/bin/neurostack.js
low Mutating tool "vault_write_file" declares no destructiveHintMTC-CAP-005
Tool "vault_write_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool vault_write_file
low Mutating tool "vault_delete_file" declares no destructiveHintMTC-CAP-005
Tool "vault_delete_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool vault_delete_file
low Shell/command execution in packaging/dev tooling (npm/postinstall.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`npm/postinstall.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: { execSync } = require("child_process"); const fs = require("fs"); const path = require("path"); const os = require("os"
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 npm/postinstall.js
low Shell/command execution in packaging/dev tooling (tests/test_file_tools.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_file_tools.py:38`): 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: etedProcess: return subprocess.run( ["git", *args], cwd=str(cwd), check=check, capture_output=True,
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 tests/test_file_tools.py
Tools 24
Each tool and what it can reach — statically extracted from the published source.
vault_delete_filewrites filesvault_list_filesreads sensitive datavault_read_filereads sensitive datavault_write_filewrites filessession_briefno sensitive capabilityvault_askno sensitive capabilityvault_communitiesno sensitive capabilityvault_contextno sensitive capabilityvault_forgetno sensitive capabilityvault_graphno sensitive capability
Show 14 more tools ↓
vault_harvestno sensitive capabilityvault_memoriesno sensitive capabilityvault_mergeno sensitive capabilityvault_prediction_errorsno sensitive capabilityvault_record_usageno sensitive capabilityvault_relatedno sensitive capabilityvault_rememberno sensitive capabilityvault_searchno sensitive capabilityvault_session_endno sensitive capabilityvault_session_startno sensitive capabilityvault_statsno sensitive capabilityvault_summaryno sensitive capabilityvault_triplesno sensitive capabilityvault_update_memoryno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (24 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 |
|---|---|---|---|---|
v0.16.0 latest |
A 93/100 | 13 | 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 neurostack --online --registry pypiOther implementations of Neurostack 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
Build, maintain, and search your knowledge vault with AI
More in Learning & Documentation
stdio compatibility bridge for the hosted AgentMail MCP server
MCP server for Alfa documentation retrieval
MCP server providing Alpine.js documentation and reference
Search the official Astro framework documentation.
MCP server providing ATAG 2.0 (Authoring Tool Accessibility Guidelines) guidance for authoring tool developers
Aurais Research Reader as an MCP server — paste a paper or article, get a structured read with verbatim-verified quotes + a signed Vorion proof chain (via @vorionsys/aurais-core).