meok-mcp-injection-scan-mcp
meok-mcp-injection-scan-mcp
2026년 4월 CVE 웨이브에서 공개된 프롬프트 인젝션 / 도구 오염 / SSRF 클래스에 대해 모든 MCP 서버를 스캔하세요.
pip install meok-mcp-injection-scan-mcp이 도구가 존재하는 이유
2026년 4월은 MCP에게 힘든 달이었습니다. Anthropic은 약 7,000개의 공개 서버(약 1억 5천만 다운로드)에 영향을 미치는 "설계상(by-design)" MCP RCE 클래스를 발표했습니다. mcp-server-git은 CVE 체인을 배포했고, DockerDash는 인젝션 체인에 의해 뚫렸습니다. 도구 설명 프롬프트 인젝션("도구 오염")은 모든 주요 MCP 호스트를 대상으로 입증되었습니다.
운영 환경에서 MCP 서버를 실행 중이거나 도입 전 감사를 수행하는 경우, 2026년 4월 공개된 패턴을 식별하는 빠른 스캔이 필요합니다. 이 MCP가 바로 그 스캔 도구입니다.
Related MCP server: agent-audit
검사 항목
5단계 심각도 등급에 걸친 30개 이상의 표준 규칙:
CRITICAL(치명적) — 직접적인 RCE, 시스템 프롬프트 재정의, 자격 증명 유출 패턴, 기본값의 셸 메타 문자,
file:/// 내부 네트워크 URL (DockerDash 169.254.169.254 메타데이터 피벗 벡터).HIGH(높음) — 인코딩된 페이로드, 에이전트의 명령형 지시문, 공급망 프롬프트, 환경 변수 참조, 도구 섀도잉.
MEDIUM(중간) — 긴급성 / 권위 언어,
additionalProperties=true, 제한 없는 문자열, 도구 이름 사칭.LOW(낮음) — 지나치게 긴 설명, 너비가 0인 문자 / 양방향 재정의 문자 (U+202E PoC 벡터).
적용 범위: OWASP LLM Top 10, GenAI Red Team v1, 2026년 4월 Anthropic MCP RCE 공개 내용 및 mcp-server-git CVE 체인.
노출된 도구
도구 | 목적 |
| 원격 MCP 서버의 도구 목록을 가져와 스캔 |
| 붙여넣은 JSON 도구 목록 스캔 (인증이 필요한 서버) |
| 조달 등급의 서명된 인증서 발행 (Pro 등급) |
| 구독 전 전체 규칙 카탈로그 검사 |
| 구독 링크 + 등급 비교 |
가격
등급 | 가격 | 제공 사항 |
무료 | £0 | 일일 5회 스캔, 서명된 보고서 없음 |
Starter | 무제한 스캔 + 서명된 보고서 | |
Pro | + 예약 재스캔 + 48시간 지원 | |
Enterprise | + 맞춤형 규칙 팩 + 4시간 SLA |
모든 서명된 인증서는 https://meok-attestation-api.vercel.app/verify/<cert_id>에 저장되며, 감사자와 조달 팀은 계정 없이 확인할 수 있습니다.
제공되지 않는 기능
이 도구는 정적 패턴 스캐너입니다. 동적 오염 분석을 실행하거나, 적대적 입력으로 서버를 퍼징하거나, 인간 레드팀을 대체하지 않습니다. 이 도구는 5초 만에 무료로 감사의 첫 80%를 수행합니다.
MEOK AI Labs 제작
1인 창업자. 런던. PyPI에 234개의 MCP 패키지. meok-attestation-api.vercel.app에서 실시간 서명 인프라 운영. 스토어프론트 councilof.ai. 카탈로그 확인: https://meok-attestation-api.vercel.app/catalogue.
배포 채널
PyPI:
pip install meok-mcp-injection-scan-mcp(본 패키지)Apify Store (이벤트당 결제): https://apify.com/knowing_yucca/meok-mcp-injection-scan
GitHub (소스): https://github.com/CSOAI-ORG/MEOK-LABS/tree/main/mcps/meok-mcp-injection-scan-mcp
Available Tools
5 toolsaudit_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
Scored across 5 tools
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.
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.
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.
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
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceScans 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.19MIT
- AlicenseNot gradedqualityCmaintenanceSecurity scanner for MCP servers. Detects prompt injection, command injection, auth bypass, and excessive permissions across tools, resources, and prompts.45 npm3MIT
- AlicenseNot gradedqualityCmaintenanceScans MCP servers, AI agent skills, and plugins for 68+ malicious patterns including credential exfiltration, prompt injection, and code execution.5MIT
- AlicenseBqualityDmaintenanceAutomated security red-team for any MCP server that scans manifests against OWASP LLM Top 10 and MCP-specific risks, returning a 0-100 hardening score and HMAC-signed report.7MIT