OWASP MCP Top 10 | OWASP Foundation
The OWASP MCP Top 10 (2025) is a living-document taxonomy of the ten most critical vulnerability classes affecting Model Context Protocol-based AI systems, covering issues like token mismanagement, privilege escalation via scope creep, tool poisoning, MCP-specific supply chain and dependency tampering, command injection, prompt injection via contextual payloads, weak authN/authZ, missing audit/telemetry, shadow MCP servers, and context injection/over-sharing. It targets AI/ML developers and security practitioners building agentic, model-chaining, and multi-modal MCP deployments, giving them a common vocabulary and checklist for secure design and auditing analogous to the OWASP Top 10 for LLM Applications.
Technologies named here
Techniques named here
- MCP01:2025 - Token Mismanagement & Secret Exposure
- MCP02:2025 - Privilege Escalation via Scope Creep
- MCP03:2025 - Tool Poisoning
- MCP05:2025 - Command Injection & Execution
- MCP06:2025 - Prompt Injection via Contextual Payloads
- MCP07:2025 - Insufficient Authentication & Authorization
- MCP08:2025 - Lack of Audit and Telemetry
- MCP09:2025 - Shadow MCP Servers
- MCP10:2025 - Context Injection & Over-Sharing
Related in AI Security
