Vibemaster MCP Server
vibemaster-mcp
npm
v8.0.2
Published by snaiilydevelopment — 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.
The only MCP that makes Claude think like a senior engineer — memory, GSD planning, auto-review, quality scoring, GitHub Action CI. 58 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 − 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 22
high Reads a sensitive credential path or dumps the environment (dist/security/secret-guard.js)MTC-SRC-006
In the server's implementation (`dist/security/secret-guard.js:105`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: Use NPM_TOKEN env var or .npmrc with env reference' }, { name: 'twilio_key', sev
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/security/secret-guard.js
high Dynamic code execution in server code (dist/analysis/session-pattern-tracker.js)MTC-SRC-001
In the server's implementation (`dist/analysis/session-pattern-tracker.js:285`): 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: any user input reaches eval(), it is full Remote Code Execution.', sessionFix: 'Delete every eval(). Us
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/analysis/session-pattern-tracker.js
high Dynamic code execution in server code (dist/detectors/bug-detector.js)MTC-SRC-001
In the server's implementation (`dist/detectors/bug-detector.js:62`): 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: nation: 'Query contains eval() or Function() which can execute arbitrary code', fix: 'Never use eval().
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/detectors/bug-detector.js
high Dynamic code execution in server code (dist/detectors/dataflow-analyzer.js)MTC-SRC-001
In the server's implementation (`dist/detectors/dataflow-analyzer.js:259`): 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: d data to \`eval()\`, \`new Function()\`, or \`exec()\`. Redesign to avoid dynamic code execution entirely.`
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/detectors/dataflow-analyzer.js
high Dynamic code execution in server code (dist/detectors/fix-suggester.js)MTC-SRC-001
In the server's implementation (`dist/detectors/fix-suggester.js:182`): 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: fixed: '// REMOVE eval(). Use JSON.parse() for data, Function() never. There is always a safer alternative.',
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/detectors/fix-suggester.js
high Shell/command execution in server code (dist/detectors/bug-detector.js)MTC-SRC-002
In the server's implementation (`dist/detectors/bug-detector.js:618`): 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: iable interpolated into exec()', explain: () => 'Interpolating variables into shell commands allows arbitrar
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/detectors/bug-detector.js
high Shell/command execution in server code (dist/detectors/dataflow-analyzer.js)MTC-SRC-002
In the server's implementation (`dist/detectors/dataflow-analyzer.js:259`): 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: `new Function()\`, or \`exec()\`. Redesign to avoid dynamic code execution entirely.` },
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/detectors/dataflow-analyzer.js
high Shell/command execution in server code (dist/detectors/stack-detector.js)MTC-SRC-002
In the server's implementation (`dist/detectors/stack-detector.js:3`): 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: port { execSync } from 'child_process'; export class StackDetector { /** * Scan a project directory and detect
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/detectors/stack-detector.js
high Shell/command execution in server code (dist/diff/diff-detector.js)MTC-SRC-002
In the server's implementation (`dist/diff/diff-detector.js: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: ort { spawnSync } from 'child_process'; import { SkillRegistry } from '../skills/registry.js'; import { SecretGuard } fr
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/diff/diff-detector.js
high Shell/command execution in server code (dist/gsd/uat.js)MTC-SRC-002
In the server's implementation (`dist/gsd/uat.js: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: nSync } = await import('child_process'); const result = spawnSync('cargo', ['check'], {
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/gsd/uat.js
high Shell/command execution in server code (dist/handlers/sync-handlers.js)MTC-SRC-002
In the server's implementation (`dist/handlers/sync-handlers.js: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: nSync } = await import('child_process'); const tscResult = spawnSync('npx', ['tsc', '--noEmit'], { c
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/handlers/sync-handlers.js
high Shell/command execution in server code (dist/installer/mcp-installer.js)MTC-SRC-002
In the server's implementation (`dist/installer/mcp-installer.js: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: ort { spawnSync } from 'child_process'; import fs from 'fs'; import os from 'os'; import path from 'path'; import { Secr
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/installer/mcp-installer.js
high Shell/command execution in server code (dist/observability/mcp-health.js)MTC-SRC-002
In the server's implementation (`dist/observability/mcp-health.js: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: import { spawn } from 'child_process'; export class MCPHealthChecker { static async checkAll(mcps) { 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 dist/observability/mcp-health.js
high Shell/command execution in server code (dist/quality/context-builder.js)MTC-SRC-002
In the server's implementation (`dist/quality/context-builder.js:62`): 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: nSync } = await import('child_process'); const result = spawnSync('git', ['log', '--oneline', '-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 dist/quality/context-builder.js
high Shell/command execution in server code (dist/setup-wizard.js)MTC-SRC-002
In the server's implementation (`dist/setup-wizard.js: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: port { execSync } from 'child_process'; const VERSION = '8.0.1'; const BOLD = '\x1b[1m'; const DIM = '\x1b[2m'; const GR
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/setup-wizard.js
low Dynamic code execution in packaging/dev tooling (dist/__tests__/debug-handlers.test.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/debug-handlers.test.js:27`): 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: input: 'const x = eval("code")', format: 'json' }); const parsed = JSON.parse(result.c
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/__tests__/debug-handlers.test.js
low Dynamic code execution in packaging/dev tooling (dist/__tests__/debug-session-step-order.test.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/debug-session-step-order.test.js:91`): 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: input: 'const token = eval("unsafe"); // summary-utility-check', mode: 'code' }); const te
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/__tests__/debug-session-step-order.test.js
low Dynamic code execution in packaging/dev tooling (dist/__tests__/diff-agentic-handlers.test.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/diff-agentic-handlers.test.js:22`): 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: changed: 'const x = eval("1");', language: 'typescript' }); expect(result.isError).toBeF
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/__tests__/diff-agentic-handlers.test.js
low Dynamic code execution in packaging/dev tooling (dist/__tests__/orchestration-handlers.test.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/orchestration-handlers.test.js:36`): 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: buggyCode = 'const x = eval("dangerous");'; const result = await handleApplyFixes(mockOrchestrator, { code: bug
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/__tests__/orchestration-handlers.test.js
low Dynamic code execution in packaging/dev tooling (dist/__tests__/pipeline-mode-gating.test.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/pipeline-mode-gating.test.js:27`): 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: input: 'const x: any = eval("code");', pipeline_mode: 'fast', }); const text = result.conte
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/__tests__/pipeline-mode-gating.test.js
low Dynamic code execution in packaging/dev tooling (dist/__tests__/runtime-events.test.js)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/runtime-events.test.js:172`): 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: code: 'const risky = eval("boom");', fix: 'Remove eval()', explanation: 'eval() execu
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/__tests__/runtime-events.test.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"vibemaster-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 dist/setup-wizard.js || echo Setup skipped. Run: npx vibemaster-mcp-setup
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package vibemaster-mcp
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|---|---|
v8.0.2 latest |
A 92/100 | 22 | 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 vibemaster-mcp --onlineMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.