Skip to main content
Glama
meok-mcp-injection-scan-mcp

meok-mcp-injection-scan-mcp

meok-mcp-injection-scan-mcp MCP server MCP Registry PyPI

meok-mcp-injection-scan-mcp MCP server

meok-mcp-injection-scan-mcp

PyPI version PyPI downloads License: MIT MEOK AI Labs

Scannen Sie jeden MCP-Server auf die Klasse von Prompt-Injection / Tool-Poisoning / SSRF, die in der CVE-Welle vom April 2026 offengelegt wurde.

pip install meok-mcp-injection-scan-mcp

Warum existiert dieses Tool?

Der April 2026 war ein schlechter Monat für MCP. Anthropic veröffentlichte eine "by-design" MCP-RCE-Klasse, die etwa 7.000 öffentliche Server (ca. 150 Mio. Downloads) betraf. mcp-server-git lieferte eine CVE-Kette aus. DockerDash wurde durch eine Injection-Kette kompromittiert. Tool-Description-Prompt-Injection ("Tool Poisoning") wurde gegen jeden großen MCP-Host demonstriert.

Wenn Sie einen MCP-Server in der Produktion betreiben oder einen vor der Einführung prüfen, benötigen Sie einen schnellen Scan, der die Muster markiert, auf die die Offenlegungen vom April 2026 abzielen. Dieses MCP ist dieser Scan.

Related MCP server: agent-audit

Was wird geprüft?

Über 30 kanonische Regeln in 5 Schweregraden:

  • CRITICAL — direkte RCE, System-Prompt-Überschreibung, Muster für Anmeldedaten-Exfiltration, Shell-Metazeichen in Standardwerten, file:// / interne Netzwerk-URLs (der DockerDash 169.254.169.254 Metadaten-Pivot-Vektor).

  • HIGH — kodierte Payloads, imperative Anweisungen an den Agenten, Supply-Chain-Prompts, Umgebungsvariablen-Referenzen, Tool-Shadowing.

  • MEDIUM — Dringlichkeits- / Autoritätssprache, additionalProperties=true, unbegrenzte Strings, Tool-Name-Impersonation.

  • LOW — überlange Beschreibungen, Zero-Width- / Bidi-Override-Zeichen (der U+202E PoC-Vektor).

Die Abdeckung entspricht: OWASP LLM Top 10, GenAI Red Team v1, der Anthropic MCP RCE-Offenlegung vom April 2026 und der mcp-server-git CVE-Kette.

Verfügbare Tools

Tool

Zweck

scan_mcp_url(url)

Ruft die Tool-Liste eines Remote-MCP-Servers ab und scannt sie

audit_tool_descriptions(tools_json)

Scannt eine eingefügte JSON-Tool-Liste (für Server mit Authentifizierung)

signed_safety_report(subject, findings_json, score, note)

Stellt ein signiertes Zertifikat in Beschaffungsqualität aus (Pro-Stufe)

list_rules()

Überprüft den vollständigen Regelkatalog vor dem Abonnement

pricing()

Abonnement-Links + Vergleich der Stufen

Preisgestaltung

Stufe

Preis

Was Sie erhalten

Free

£0

5 Scans / Tag, keine signierten Berichte

Starter

£29/mo

Unbegrenzte Scans + signierte Berichte

Pro

£79/mo

+ geplante Rescans + 48h Support

Enterprise

£1,499/mo

+ benutzerdefinierte Regelpakete + 4h SLA

Jedes signierte Zertifikat befindet sich unter https://meok-attestation-api.vercel.app/verify/<cert_id> — Prüfer und Beschaffungsteams können dies ohne Konto bestätigen.

Was Sie NICHT erhalten

Dies ist ein Scanner für statische Muster. Er führt keine dynamische Taint-Analyse durch, fuzzt den Server nicht mit gegnerischen Eingaben und ersetzt kein menschliches Red-Team. Es sind die ersten 80 % der Prüfung, in 5 Sekunden, kostenlos.

Entwickelt von MEOK AI Labs

Solo-Gründer. London. 234 MCP-Pakete auf PyPI. Live-Signierungsinfrastruktur unter meok-attestation-api.vercel.app. Storefront councilof.ai. Katalog abrufen: https://meok-attestation-api.vercel.app/catalogue.


Vertriebskanäle

Available Tools

5 tools
audit_tool_descriptionsA

Audit a JSON string containing a tool list (paste from your own MCP server's tools/list output). Same rule catalogue as scan_mcp_url — useful when the server is behind auth or not yet deployed.

tools_json accepts either: a raw list, or {"tools": [...]}, or {"result": {"tools": [...]}}.

Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool for security assessment, threat detection, or vulnerability analysis. Suitable for automated security scanning and risk evaluation.

When NOT to use: Do not rely solely on this tool for production security decisions. Always combine with manual security review.

Args: tools_json (str): The tools json to analyze or process. api_key (str): The api key to analyze or process.

Inputs: tools_json (required), api_key.

list_rulesA

List every detection rule in the canonical catalogue. Useful for buyers auditing what we check before subscribing.

Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool for security assessment, threat detection, or vulnerability analysis. Suitable for automated security scanning and risk evaluation.

When NOT to use: Do not rely solely on this tool for production security decisions. Always combine with manual security review. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: no named parameters.

pricingB

Pricing + subscribe links for this MCP.

Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool for security assessment, threat detection, or vulnerability analysis. Suitable for automated security scanning and risk evaluation.

When NOT to use: Do not rely solely on this tool for production security decisions. Always combine with manual security review. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: no named parameters.

scan_mcp_urlA

Fetch a remote MCP server's /tools/list (or any JSON tool listing) and scan every tool's name + description + inputSchema against the canonical 30+ injection-pattern rules.

Returns a structured report: per-tool findings, severity counts, score 0-100, verdict, and remediation hints. Free tier: 5 scans/day per key.

Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool for security assessment, threat detection, or vulnerability analysis. Suitable for automated security scanning and risk evaluation.

When NOT to use: Do not rely solely on this tool for production security decisions. Always combine with manual security review.

Args: url (str): The url to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: url (required), api_key.

signed_safety_reportA

Issue a cryptographically signed safety report for the scanned MCP server. Returns a cert with a public verify URL anyone can hit to confirm the audit happened on the date claimed.

Pro / Enterprise tier only.

Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool for security assessment, threat detection, or vulnerability analysis. Suitable for automated security scanning and risk evaluation.

When NOT to use: Do not rely solely on this tool for production security decisions. Always combine with manual security review.

Args: subject (str): The subject to analyze or process. findings_json (str): The findings json to analyze or process. score (int): The score to analyze or process. note (str): The note to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: subject (required), findings_json, score, note, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of the security scanning workflow: 'audit_tool_descriptions' handles local JSON analysis, 'scan_mcp_url' handles remote scanning, 'list_rules' lists detection rules, 'pricing' provides subscription details, and 'signed_safety_report' generates a signed certificate. No two tools have overlapping purposes.

    Naming Consistency3/5

    The naming convention is mostly snake_case but inconsistent in structure: three tools follow a verb_noun pattern ('audit_tool_descriptions', 'list_rules', 'scan_mcp_url'), while 'pricing' is a bare noun and 'signed_safety_report' uses a past participle adjective-noun form. This mix reduces predictability.

    Tool Count5/5

    With 5 tools, the server is well-scoped for its purpose of scanning MCP servers for injection vulnerabilities. Each tool serves a clear function without overlap, and the count is appropriate for a focused security assessment tool.

    Completeness4/5

    The tool surface covers the core workflow: local audit, remote scan, rule listing, pricing, and signed reporting. Minor gaps exist (e.g., no tool for configuration or result history), but these are not essential for the primary use case. Overall, the surface is sufficiently complete for its domain.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Scans MCP servers for prompt injection, supply chain attacks, excessive permissions, and code execution risks. Includes an offline blacklist that catches known-compromised packages like LiteLLM 1.82.7/1.82.8 and Trivy with zero latency.
      19
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Security scanner for MCP servers. Detects prompt injection, command injection, auth bypass, and excessive permissions across tools, resources, and prompts.
      45 npm
      3
      MIT