Topic starter
24/06/2026 8:07 pm
TL;DR: Secure AI agents need a layered control plane around MCP, data orchestration, and gateway enforcement so models cannot reach raw APIs or bypass policy, according to Kong. The real governance issue is that agent security depends on protocol boundaries, not on trusting the model to behave correctly.
Editorial analysis by NHI Mgmt Group, based on content published by Kong: “How to Build Secure AI Agents with Kong MCP Proxy”.
Key questions
Q: What breaks when AI agents can call backend tools directly?
A: Direct tool access collapses the boundary between model output and enterprise action.
Q: Why does protocol-level enforcement matter for AI agent governance?
A: Because agents can generate requests at runtime, governance must decide whether those requests become actions.
Q: How should security teams scope access for AI coding agents in development workflows?
A: Security teams should treat AI coding agents like any other privileged actor and scope them to the smallest task they need to complete.
Practitioner guidance
- Define an MCP enforcement boundary Place authentication, authorization, and logging in front of every agent-facing tool so the model never talks directly to raw APIs or databases.
- Expose task-scoped backend views Publish curated interfaces that return only the data and functions required for the specific agent task, and remove direct access to backend schemas.
- Instrument every tool invocation Log each MCP call, request context, and denied action so security teams can audit what the agent attempted and why it was blocked.
Bottom line: AI agents need governed tool boundaries because direct model access to backend systems turns prompts into execution risk.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
25/06/2026 5:18 am
Protocol boundaries, not model intent, now define the control surface for AI agents. The article is describing a shift from prompt-level trust to tool-level governance, which is the right mental model for agentic AI. Once a system can independently call tools, the security question becomes which capabilities are exposed, under what policy, and with what audit trail. Practitioners should treat the protocol boundary as the enforcement point, not the model output.
A few things that frame the scale:
- 88% of organisations have embedded AI agents in their workflows, according to KPMG's 2026 report.
A question worth separating out:
Q: How do teams know whether agent tool controls are working?
A: They are working when every allowed call is attributable, every disallowed call is blocked at the gateway, and the agent cannot reach systems outside its exposed MCP endpoints. If the model can still influence backend behavior outside those paths, the control boundary is incomplete.
👉 Read our full editorial: Secure AI agents need protocol-level controls, not model trust