MCP is becoming the default integration layer between AI clients and tools, and it ships with structural gaps every deployment inherits: no input validation story, no audit requirement, no rate limiting, auth left to the server author. Rather than repeat the ecosystem's warnings, we scanned it — 8,216 MCP servers classified by auth appropriateness, 7,522 agent skills statically analyzed for credential leaks and injection patterns — and wrote up each risk class with what actually mitigates it.
The six structural risks are collected in the MCP Security series; the checklist post below is the practical starting point. For the layer that closes most of these by construction, see what an MCP control plane is.