GhostCrab MCP Server
@mindflight/ghostcrab-personal-mcp
npm
v0.6.7
Published by @mindflight — 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.
SQLite-backed personal memory server with a MindBrain and Zig backend.
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 13
high Shell/command execution in server code (bin/commands/brain-db-who.mjs)MTC-SRC-002
In the server's implementation (`bin/commands/brain-db-who.mjs: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 { existsSync } from "node:fs"; import { resolve } from "node:path"; 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 bin/commands/brain-db-who.mjs
high Shell/command execution in server code (bin/commands/brain-structured-import.mjs)MTC-SRC-002
In the server's implementation (`bin/commands/brain-structured-import.mjs: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: spawnSync } from "node:child_process"; import { resolveGhostcrabSqlite } from "../lib/resolve-ghostcrab-sqlite.mjs"; im
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/commands/brain-structured-import.mjs
high Shell/command execution in server code (bin/commands/serve.mjs)MTC-SRC-002
In the server's implementation (`bin/commands/serve.mjs: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: rt { spawn } from "node:child_process"; import { constants, existsSync, mkdirSync, openSync, readFileSync, 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 bin/commands/serve.mjs
high Shell/command execution in server code (bin/lib/brain-engine-runner.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/brain-engine-runner.mjs:1`): 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 { existsSync, readFileSync } from "node:fs"; import { dirname, join } fro
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/lib/brain-engine-runner.mjs
high Shell/command execution in server code (bin/lib/cli-invocation.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/cli-invocation.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: spawnSync } from "node:child_process"; import { existsSync, lstatSync, readFileSync, realpathSync } from "node:fs"; imp
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/lib/cli-invocation.mjs
high Shell/command execution in server code (bin/lib/install-upgrade.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/install-upgrade.mjs:1`): 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 { createHash } from "node:crypto"; import { copyFileSync, existsSync,
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/lib/install-upgrade.mjs
high Shell/command execution in server code (bin/lib/mcp-global-setup.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/mcp-global-setup.mjs: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: spawnSync } from "node:child_process"; import { resolveRuntimeNodePath } from "./runtime-node.mjs"; import { formatDl
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/lib/mcp-global-setup.mjs
high Shell/command execution in server code (bin/lib/postinstall-smoke.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/postinstall-smoke.mjs: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 { existsSync } from "node:fs"; import { 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 bin/lib/postinstall-smoke.mjs
high Shell/command execution in server code (bin/lib/prebuild-permissions.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/prebuild-permissions.mjs:12`): 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 { createHash } from "node:crypto"; import { chmodSync, existsSync, readFi
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/lib/prebuild-permissions.mjs
high Shell/command execution in server code (bin/lib/runtime-node.mjs)MTC-SRC-002
In the server's implementation (`bin/lib/runtime-node.mjs: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: spawnSync } from "node:child_process"; import { accessSync, constants } from "node:fs"; /** * @param {string} nodePat
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/lib/runtime-node.mjs
medium Dynamic module load from a non-literal (bin/lib/import-docs.mjs)MTC-SRC-005
In the server's implementation (`bin/lib/import-docs.mjs:15`): 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: title: "Structured import (tabular)", path: "docs/setup/structured-import.md" }, document: { title: "Do
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/lib/import-docs.mjs
medium Dynamic module load from a non-literal (dist/mcp/import-pipelines.js)MTC-SRC-005
In the server's implementation (`dist/mcp/import-pipelines.js:114`): 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: `- **After import (MCP):** ${p.post_import_mcp.map((t) => `\`${t}\``).join(", ")}`, `- **Full r
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/import-pipelines.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@mindflight/ghostcrab-personal-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: node ./bin/lib/postinstall-prebuilds.mjs
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @mindflight/ghostcrab-personal-mcp
Tools 1
Each tool and what it can reach — statically extracted from the published source.
readmeno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (1 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 3
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 |
|---|---|---|---|---|
v0.6.7 latest |
A 92/100 | 13 | 1.13.0 | 2026-09-05 |
v0.6.6 |
A 92/100 | 13 | 1.13.0 | 2026-09-04 |
v0.6.5 |
A 92/100 | 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 @mindflight/ghostcrab-personal-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