TL;DR: MCP security best practices put confused deputy risk at the center of MCP authorization, because Aembit says sessions and token passthrough do not show who is actually acting. MCP servers need per-request checks so client, audience and operation stay explicit.
Editorial analysis by NHI Mgmt Group, based on content published by Aembit: “MCP Authentication and Authorization Patterns”.
Key questions
Q: Why do token audience checks matter so much in MCP?
A: Token audience checks matter because a valid token for one service should not be reusable against another service.
Q: What are the signs that an MCP authorization model is too loose?
A: Warning signs include token passthrough between components, broad token scopes, shared sessions for workloads, and redirect URI patterns that accept wildcards or partial matches.
Q: What breaks when MCP relies on sessions instead of request-level authorization?
A: Session-based authentication breaks because MCP requests can be generated dynamically by nonhuman identities and routed through tools or intermediaries that were never part of the original trust decision.
Practitioner guidance
- Enforce client-bound consent Map each approved user-to-client relationship to explicit scopes, then reject requests that do not match the approved client identifier and operation.
- Eliminate session authentication Remove session cookies and other server-maintained authentication state from MCP flows, and require token validation on every request instead.
- Block token passthrough Validate tokens directly with the authorization server and use token exchange for downstream access rather than forwarding the original token.
Bottom line: MCP security best practices are built around confused deputy prevention, not just login verification or token issuance.
Glossary terms: Confused Deputy, Token Passthrough, Audience Validation, Per-Client Consent
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Confused deputy risk is the right mental model for MCP governance. MCP is not simply about authenticating agents or hardening API calls. It is about stopping a legitimate server from applying valid authority to the wrong client or operation, which is why per-client consent and audience validation sit at the center of the specification. Practitioners should treat authorization binding, not login success, as the control boundary.
A few things that frame the scale:
- 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: How do organisations decide whether MCP should use OAuth, mTLS, or federation?
A: Use OAuth 2.1 for standard delegated access, mTLS for higher assurance between tightly controlled workloads, and federation when identity must span cloud or on-premises domains. The decision should follow the trust boundary, the exposure of the token path, and the operational maturity of the workload identity stack, not personal preference.
👉 Read our full editorial: MCP security best practices expose the confused deputy risk