Skills and MCP: what security teams need to govern in production

TL;DR: Skills do not replace MCP, but they change how agents decide when to use tools, according to Obot’s coverage of Pedro Rodrigues’ MCP Dev Summit talk. The practical issue is governance: if agents can compose actions from stale context or unvetted instructions, the control plane must cover both protocol access and skill approval.

NHIMG editorial — based on content published by Obot: Skills Are Not the MCP Killer

By the numbers:

• 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, sharing sensitive data, and revealing access credentials.

Questions worth separating out

Q: How should teams govern skills and MCP together in production?

A: Treat MCP as the protocol boundary and skills as governed instruction assets.

Q: Why do AI agents create risk even when they stay within approved permissions?

A: AI agents can be authorised correctly and still produce harmful outcomes because permission is not the same as intent or behavioural appropriateness.

Q: What breaks when an agent can call tools without user context?

A: Per-user filtering, scoped authorisation, and clean audit attribution all become unreliable.

Practitioner guidance

• Separate protocol governance from instruction governance Assign distinct owners, review paths, and audit requirements for MCP servers and skills so tool access and task guidance are governed independently.
• Require approved skills for production agent runs Maintain a registry of approved skills with versioning, provenance, and change control before any agent can load them in production workflows.
• Validate tool-specific failure modes in test workflows Test whether agent actions bypass underlying controls, such as PostgreSQL row-level security, when the agent composes outputs from incomplete context.

What's in the full article

Obot's full post covers the operational detail this analysis intentionally leaves for the source:

• The live MCP versus Skills demo sequence, including the four test modes and the exact failure reproduced on stage.
• Pedro Rodrigues' benchmark framing for why agents choose stale context unless prompted to search or load the right skill.
• Obot's control-plane model for governing MCP servers and a skill registry together in production.
• The discussion of how enterprise teams should curate, approve, and audit reusable agent skills.

👉 Read Obot's analysis of why Skills and MCP belong together →

Skills and MCP: what security teams need to govern in production?

Explore further

View Full Forum →  |  NHI Foundation Course →