TL;DR: MCP servers are creating a new access layer where authentication, authorization, and secret handling decide whether AI tools stay within scope, according to Aembit. IAM teams need to treat MCP governance as identity governance, with tighter client inventory and per-tool checks.
Editorial analysis by NHI Mgmt Group, based on content published by Aembit: “How To Create an MCP Server To Connect Your App With LLMs”.
Key questions
Q: Why do MCP servers create more risk than traditional APIs?
A: MCP servers create more risk because they centralize access, make tools discoverable at runtime, and often sit close to the secrets that authenticate downstream calls.
Q: How should teams decide whether MCP access is safe enough to allow?
A: Teams should allow MCP access only when the agent or server can be bounded with explicit scopes, revocable credentials, and traceable client registration.
Q: What breaks when MCP servers rely on prompt-based access control?
A: Prompt-based control breaks because the LLM can describe intent, but it cannot reliably enforce policy.
Practitioner guidance
- Enforce server-side authentication for every MCP endpoint Require a verifiable identity layer before any tool or resource is exposed, and do not rely on local deployment assumptions or prompt behavior to establish trust.
- Apply per-tool authorization checks Bind each client to explicit roles and permissions, then evaluate access on every tool invocation so the server, not the model, decides what is allowed.
- Replace static API keys with ephemeral access Move MCP-connected workloads toward short-lived credentials and task-scoped access so a leaked secret cannot be reused across unrelated sessions.
Bottom line: MCP servers introduce a new access layer where authentication, authorization, and secret handling decide whether AI tools stay within scope.
Glossary terms: MCP Server, Per-tool authorization, Just-in-Time Access Request, Device Trust Boundary
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
MCP server security is really a governed-access problem, not an AI novelty problem. The protocol exposes a new control plane for tools, data, and actions, but the control failures are familiar: weak authentication, weak authorization, and unclear request provenance. The difference is that the caller may now be an LLM-driven client rather than a stable human user, which changes how access should be modeled. Practitioners should treat MCP as a new enforcement boundary, not a convenience layer.
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.
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: When does just-in-time access make sense for MCP-connected systems?
A: Just-in-time access makes sense when the backend permission would otherwise persist longer than the task. It is most useful for API keys, service credentials, and other non-human access paths that only need to exist briefly. The goal is to reduce standing exposure, not to replace authorization or server-side policy.
👉 Read our full editorial: MCP server governance now depends on server-enforced policy