Create Expert Brain MCP Server
@expertintegrado/create-expert-brain
npm
v3.2.0
Source verified
Published by expert-integrado — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Scaffolder do Expert Brain — um grafo de conhecimento pessoal pro Claude rodando 100% no free tier da Cloudflare.
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 − 6 = 94. 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 |
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 15
high Shell/command execution in server code (bin.mjs)MTC-SRC-002
In the server's implementation (`bin.mjs:21`): 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 path from 'node:path'; import { fileURLToPath } from 'node:url'; const _
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.mjs
medium Hardcoded egress to an external endpoint (template/src/notify.ts)MTC-SRC-003
In the server's implementation (`template/src/notify.ts:114`): 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 res = await fetch(`https://api.telegram.org/bot${env.TELEGRAM_BOT_TOKEN}/sendMessage`, { method: 'POST',
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 template/src/notify.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/backup.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/backup.test.ts:33`): 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 res = await SELF.fetch('https://x.test/app/export', { redirect: 'manual' }); expect(res.status).toBe(302);
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 template/src/web/backup.test.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/config.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/config.test.ts:21`): 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 res = await SELF.fetch('https://x.test/app/config', { redirect: 'manual' }); expect(res.status).toBe(302);
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 template/src/web/config.test.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/graph-prefs.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/graph-prefs.test.ts:92`): 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 res = await SELF.fetch('https://x.test/app/graph/prefs', { method: 'POST', headers: { cookie: await 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 template/src/web/graph-prefs.test.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/graph.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/graph.test.ts:30`): 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 res = await SELF.fetch('https://x.test/app/graph/data', { redirect: 'manual' }); expect(res.status).toBe(302)
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 template/src/web/graph.test.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/login.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/login.test.ts:7`): 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 res = await SELF.fetch('https://x.test/app/login'); expect(res.status).toBe(200); const html = await res.
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 template/src/web/login.test.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/notes.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/notes.test.ts:34`): 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 res = await SELF.fetch('https://x.test/app/notes', { redirect: 'manual' }); expect(res.status).toBe(302);
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 template/src/web/notes.test.ts
low Hardcoded egress to an external endpoint in packaging/dev tooling (template/src/web/taxonomy-config.test.ts)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`template/src/web/taxonomy-config.test.ts:151`): 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 res = await SELF.fetch('https://x.test/app/config/taxonomy', { method: 'POST', headers: { 'content-ty
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 template/src/web/taxonomy-config.test.ts
low Shell/command execution in packaging/dev tooling (template/scripts/deploy.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`template/scripts/deploy.mjs:11`): 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 } from 'node:child_process'; const isWin = process.platform === 'win32'; function fail(msg) { console.err
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 template/scripts/deploy.mjs
low Shell/command execution in packaging/dev tooling (template/scripts/restore-from-snapshot.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`template/scripts/restore-from-snapshot.mjs:23`): 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 { jsonlToInsertStatements, sortTablesForRestore } from './lib/jsonl-to-sq
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 template/scripts/restore-from-snapshot.mjs
low Shell/command execution in packaging/dev tooling (template/scripts/seed-dev.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`template/scripts/seed-dev.mjs:29`): 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 } from 'node:child_process'; import fs from 'node:fs'; import path from 'node:path'; const args = process.ar
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 template/scripts/seed-dev.mjs
low Shell/command execution in packaging/dev tooling (template/scripts/setup.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`template/scripts/setup.mjs:25`): 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 { readFileSync, writeFileSync, existsSync, copyFileSync } from 'node:fs';
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 template/scripts/setup.mjs
low Shell/command execution in packaging/dev tooling (template/scripts/ux-audit/audit.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`template/scripts/ux-audit/audit.py:46`): 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: return subprocess.check_output( ["git", "rev-parse", "--short", "HEAD"], cwd=Pa
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 template/scripts/ux-audit/audit.py
low Shell/command execution in packaging/dev tooling (template/scripts/verify-wave.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`template/scripts/verify-wave.mjs: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: spawnSync } from 'node:child_process'; import process from 'node:process'; const args = process.argv.slice(2); const p
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 template/scripts/verify-wave.mjs
Tools 32
Each tool and what it can reach — statically extracted from the published source.
attach_media_to_noteno sensitive capabilitycaptureno sensitive capabilitycomment_taskno sensitive capabilitycomplete_taskno sensitive capabilitydelete_linkno sensitive capabilitydelete_noteno sensitive capabilitydelete_note_mediano sensitive capabilitydigestno sensitive capabilityexpandno sensitive capabilityget_contactno sensitive capability
Show 22 more tools ↓
get_contact_by_phoneno sensitive capabilityget_noteno sensitive capabilityget_note_mediano sensitive capabilityget_taskno sensitive capabilitylinkno sensitive capabilitylist_contactsno sensitive capabilitylist_inboxno sensitive capabilitylist_tasksno sensitive capabilitylist_tasks_due_todayno sensitive capabilitymark_privateno sensitive capabilityrecallno sensitive capabilityreembedno sensitive capabilityresolve_inboxno sensitive capabilityrestore_noteno sensitive capabilitysave_noteno sensitive capabilitysave_taskno sensitive capabilitysearch_contactsno sensitive capabilityshare_taskno sensitive capabilitystatsno sensitive capabilityunshare_taskno sensitive capabilityupdate_noteno sensitive capabilityupdate_taskno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (32 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 |
|---|---|---|---|---|
v3.2.0 latest |
A 94/100 | 15 | 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 @expertintegrado/create-expert-brain --onlineMore in Productivity & Workflow
MCP AgentChat - 让 AI Agent 通过 Telegram 与用户实时交互：发送消息、图片，等待用户回复
A Model Context Protocol (MCP) server for Airthings Air Quality Monitor devices.
MCP server for Anki
TypeScript package for reading and searching Apple Notes on macOS via direct SQLite access. Includes markdown conversion, attachment support, and offers a local MCP server!
Verified biotech catalyst calendar (PDUFA/AdComm/trial readouts) anchored to official sources.
Appointment booking platform letting agents check provider availability and create bookings.