MCP vs. skills: what governance gap do teams miss?

TL;DR: MCP and Skills solve different problems for AI agents, according to JetStream Security: MCP exposes tools and data sources, while Skills provide the instructions that shape how those tools are used. The governance challenge is not choosing between them, but controlling how they are stacked, scoped, and revoked at runtime.

Editorial analysis by NHI Mgmt Group, based on content published by JetStream Security: “MCP vs. Skills: A False Debate”.

Key questions

Q: What breaks when AI agents can chain tools through MCP without tight policy controls?

A: What breaks is the separation between request, authorisation, and execution.

Q: Why do stacked MCP and Skill workflows increase governance risk?

A: Because each added component expands either the agent’s reachable systems or the instruction surface that shapes its actions.

Q: How should teams govern AI agents that use tools during evaluation?

A: Treat the agent’s permissions as part of the test itself.

Practitioner guidance

• Define the agent runtime contract Document which MCP servers, Skills, and identities are permitted for each workflow before it moves beyond pilot use.
• Separate tool approval from instruction approval Review MCP connectivity and Skill content as distinct governance decisions, because each changes risk in a different way.
• Scope destructive tools out of routine workflows Block actions such as delete, write, or submit unless the task explicitly needs them and the workflow owner can justify them.

Bottom line: MCP and Skills solve different problems, but the governance failure appears when teams treat them as competing substitutes instead of complementary controls.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →