Topic starter
06/07/2026 9:38 am
TL;DR: Developers built secure AI agents and MCP servers with scoped permissions, outbound apps, and agent-specific tokens across productivity, healthcare, security, and identity use cases in Descope’s first Global MCP Hackathon. The core lesson is that once agents can authenticate and act across systems, identity design becomes the control plane, not an afterthought.
Editorial analysis by NHI Mgmt Group, based on content published by Descope: “Announcing Winners of the Descope Global MCP Hackathon!”.
Key questions
Q: How should security teams govern MCP servers used by AI coding assistants?
A: Treat MCP servers as privileged trust boundaries, not simple data sources.
Q: Why do scoped tokens matter for agentic workflows?
A: Scoped tokens matter because agents act at runtime and may reach multiple systems through one delegated path.
Q: What breaks when an agent identity is reused across multiple workflows?
A: Reused identities collapse separation of purpose and widen blast radius.
Practitioner guidance
- Define agent identity boundaries before tool access Map every agent to a specific role, permitted tool set, and revocation path before it can call any MCP server or outbound app.
- Replace embedded credentials with scoped delegation Use scoped tokens and OAuth-based flows instead of hardcoded secrets so each workflow has a distinct, revocable authorization path.
- Separate orchestrator and sub-agent privileges Give planner, executor, and reviewer agents different identities so one compromised or overreaching component cannot inherit the whole workflow.
Bottom line: MCP changes the security question from whether a tool is exposed to which identity is allowed to invoke it and under what scope.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
06/07/2026 9:53 am
Identity is now the control plane for agent execution: Once an agent can authenticate and invoke tools, the security boundary moves from the prompt to the permission model. The hackathon entries show that useful agent systems are built on scoped delegation, revocable access, and explicit tool boundaries. That makes identity design an execution requirement, not a separate governance discussion.
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 teams know if agent access is staying inside its intended scope?
A: Measure execution-level evidence, not just identity events. Look for tool calls, resource access, action sequences, and revocation behaviour tied to a specific task. If the only evidence is authentication and token issuance, you do not have enough signal to judge scope adherence.
👉 Read our full editorial: MCP hackathon results show secure identity is now agent infrastructure