---
id: 5704
title: "How to govern agentic AI, MCPs, and AI code assistants"
source_domain: about.gitlab.com
source_url: "https://about.gitlab.com/blog/govern-agentic-ai-mcps-code-assistants/"
published_at: "2026-07-31T00:00:00Z"
tags: ["ai-security", "agentic-ai", "gitlab", "devsecops", "ai-governance", "access-control", "mcp", "governance"]
phying_url: "https://phying.com/item/5704"
lang: en
---

# How to govern agentic AI, MCPs, and AI code assistants

## Summary

GitLab outlines a governance framework for agentic AI and MCP-enabled coding assistants, covering access, authorization, human review points and audit evidence as agents push code and touch CI/CD.

## Intelligence Metadata

- **Sources:** about.gitlab.com
- **Published:** 2026-07-31T00:00:00Z
- **Original:** https://about.gitlab.com/blog/govern-agentic-ai-mcps-code-assistants/
- **Phying News:** https://phying.com/item/5704