shipcheck-mcp
shipcheck-mcp
MCP-Server, der es KI-Coding-Agenten ermöglicht, Shipcheck auf lokalen JavaScript- und TypeScript-Repositories auszuführen.
Shipcheck scannt von KI erstellte Apps auf Startrisiken wie offengelegte, potenziell private Umgebungsvariablen, unsignierte Stripe-Webhooks, fehlende Nachweise für Supabase/Firebase-Regeln, Debug-Routen, fehlende KI-Nutzungsrichtlinien, fehlende CI, lockere Abhängigkeiten und unzureichende Release-Dokumentation.
Tool-Seite: https://tatelyman.github.io/tate-web-services/shipcheck.html
Offizielles MCP-Register: https://registry.modelcontextprotocol.io/v0/servers?search=shipcheck
Demo-Repo mit GitHub-Code-Scanning-Warnungen: https://github.com/TateLyman/shipcheck-demo-ai-app
Installation
Direkt mit npx ausführen:
npx --yes shipcheck-mcpRelated MCP server: CodeInspectus
MCP-Konfiguration
Fügen Sie diesen Server einem MCP-Client hinzu, der stdio-Server unterstützt:
{
"mcpServers": {
"shipcheck": {
"command": "npx",
"args": ["--yes", "--package", "shipcheck-mcp", "shipcheck-mcp"]
}
}
}Tool
scan_repository
{
"root": ".",
"format": "markdown",
"failOn": "medium",
"strict": true
}Formate: text, markdown, json oder sarif.
Schweregrade: info, low, medium oder high.
Shipcheck ist eine defensive statische Analyse, kein Penetrationstest. Führen Sie es nur auf Repositories aus, die Sie besitzen oder für die Sie eine Inspektionsberechtigung haben.
Entwicklung
npm install
npm run checkAvailable Tools
1 toolscan_repositoryScan repository with ShipcheckB
Run Shipcheck on a local JavaScript or TypeScript repo the user owns or is authorized to inspect.
Inputs: root, format, failOn, strict.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no chance of confusion between tools. The single tool has a clear and distinct purpose.
With only one tool, there are no naming inconsistencies. The name 'scan_repository' follows a clear snake_case convention.
A single tool feels thin for most purposes, though for a very specialized server like 'shipcheck' it might be acceptable. It borders on too minimal.
The server only offers one operation (scanning), which may be insufficient for a full workflow. Missing potential tools like listing results or configuration, but the core task is covered.
Maintenance
Related MCP Connectors
Checks AI-written code for leaked keys and made-up packages, on your machine. Never uploads code.
Security scanner for AI-written code: SAST, secrets, dependencies, IaC, containers and DAST.
Lets coding agents check their own code for leaked secrets, risky dependencies and AI-code mistakes
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLocal-first security check for AI coding agents — finds hardcoded secrets, exposed .env files, git-history leaks and vulnerable dependencies (OSV), entirely on your machine. Ask your agent "is this safe to ship?" and get a Launch Readiness score with a fix for every finding.MIT
- AlicenseAqualityBmaintenanceLocal-first, zero-egress security scanner for AI-generated / "vibe-coded" JS/TS. Bundles Opengrep, Gitleaks & Trivy behind one CWE-keyed schema and adds AI-code-specific checks (client-side secret exposure, Supabase RLS, prompt-injection & LLM-output XSS sinks). No account, no telemetry.10358 npm51Apache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides security checks for AI agents, including secret scanning, CVE lookup, and dependency vulnerability scanning, all running locally except for CVE lookups.MIT
- AlicenseBqualityBmaintenanceEnables AI coding agents to perform zero-execution, AST-based static analysis of JavaScript/TypeScript codebases, including symbol lookup, dependency tracing, change-impact analysis, dead-code detection, and risk assessment.8MIT