Topic starter
24/06/2026 8:45 pm
TL;DR: Agentic AI adoption is accelerating, with 90% of organisations with visibility into their plans actively adopting AI agents, according to Kong, while the operational stack increasingly depends on LLMs plus MCP tools to make those agents useful. The security issue is that capability, access, and observability now converge in runtime infrastructure, and existing IAM models do not fully govern that convergence.
Editorial analysis by NHI Mgmt Group, based on content published by Kong: “# From Browser to Prompt: Building Infra for the Agentic Internet”.
Key questions
Q: What breaks when AI agents discover tools at runtime instead of using hardcoded lists?
A: Hardcoded lists assume the tool set is stable enough to be embedded in code.
Q: Why do MCP and agentic AI complicate IAM governance?
A: Because IAM controls are usually built around stable identities, known purposes, and review cycles that assume access remains legible long enough to inspect.
Q: What are the signs that agent tool access is becoming overprivileged?
A: Warning signs include broad tool lists, direct connections to internal systems without a broker, and authorization checks that happen only at login or launch.
Practitioner guidance
- Define MCP server tiers and limits Classify each MCP server by sensitivity, allowed agent population, and permitted operations.
- Correlate model and tool telemetry Join LLM traces, token metrics, and MCP invocation logs in a single review path.
- Govern agent discovery rules Restrict which tools agents can discover and consume at runtime, especially where those tools expose customer data or high-impact operations.
Bottom line: Agentic AI infrastructure now couples models and MCP tools, so governance has to span access, limits, and observability across the full runtime path.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
25/06/2026 5:31 am
MCP governance is becoming the missing layer between identity and AI execution: the article shows that model access alone does not govern agent behaviour if the tool layer is unconstrained. LLMs provide reasoning, but MCP determines what the agent can actually reach and combine at runtime. That makes the governance question about discoverability, scope, and traceability across a tool ecosystem, not about model choice alone. Practitioners should treat MCP as part of the identity plane for agentic systems.
A question worth separating out:
Q: How should teams decide between API governance and MCP governance for agents?
A: Use API governance for the backend service boundary and MCP governance for the agent-facing tool boundary. The two overlap, but they solve different problems: one secures the service surface, the other constrains how agents discover and consume that surface.
👉 Read our full editorial: Agentic internet infrastructure exposes new MCP governance gaps