MCP Security Risks

Each connected MCP server is a piece of untrusted text in context. Four types of risks: tool description poisoning (malicious instructions in description – injection, triggered every session); malicious or compromised servers (supply chain attack); tool shadowing (intercepting calls with sensitive parameters); credential risks (OAuth tokens, API keys). Mitigation: audit descriptions as untrusted input, server version pinning, least privilege, independent Sidecar verification.

Related: [MCP Protocol], [Sidecar Mechanism], [Deadly Triad]