A code review lens checks pull request cards using read-only context connectors and team skill folders
A code review lens checks pull request cards using read-only context connectors and team skill folders
+ Large Language Models News

GitHub makes Copilot review skills and MCP generally available

GitHub moved Copilot code review agent skills and MCP to general availability while preparing default model enablement for enterprise customers.

GitHub has made agent skills and MCP server support generally available in Copilot code review, giving automated reviews more access to team-specific instructions and external context.

The July 29 changelog says the feature is available for Copilot Pro, Pro+, Business, and Enterprise users. Agent skills use a SKILL.md file under .github/skills, while MCP server connections can pull context from tools such as issue trackers, documentation systems, and service catalogs.

GitHub says Copilot code review MCP tool calls are read-only. It also says comments generated using agent skills or MCP context now show attribution so reviewers can tell when added context shaped a comment.

Model governance is changing at the same time

GitHub also announced a default model enablement policy for Copilot Business and Enterprise. For the next 28 days, the setting is configurable but does not change user access. On August 26, generally available models that admins have not explicitly configured will follow the default policy.

If the policy remains enabled, those models become available to users. If an organization disables the policy, they stay off. GitHub says explicit enablement or disablement choices are preserved, and that open-weight models and models not covered by GitHub’s data-retention agreement are excluded.

Read together, the two changelogs show Copilot becoming more platform-like. Code review is not only a model prompt. It is a bundle of team instructions, connected context, model availability settings, attribution, and administrative policy.

The review surface needs its own controls

Automated code review has a different risk profile from autocomplete. It produces comments other engineers may treat as review evidence, and it can look across code, issues, docs, and service metadata before deciding what to flag.

That makes read-only MCP a useful constraint but not a full governance answer. Teams still need to decide which sources are appropriate for review, how sensitive context is exposed, and whether Copilot comments are advisory or blocking.

For administrators, the August 26 model-policy date is the near-term action item. If a company wants every generally available model to require explicit approval, it should change the default policy before that date.

Sources

The AI Feed Desk

The AI Feed Desk

Editorial desk

The AI Feed Desk tracks AI provider updates, model releases, agent tooling, and enterprise adoption, turning fast-moving announcements into source-linked context for builders and operators.

Noticed a typo, incorrect information, or translation error?

Tell us so we can fix it.

Help Improve This Article

Related Articles

A developer workbench shows completed agent requests with model labels, credit meters, cache indicators, and session branches

GitHub Copilot Auto now shows model and AI-credit details

GitHub Copilot's weekly release adds model, AI-credit, and cache visibility for Auto requests plus new CLI session controls.

The AI Feed Desk

By The AI Feed Desk

6 minutes ago
A comment trigger, reasoning dial, and pull request checkpoint connect through a cloud agent workspace

GitHub gives Copilot cloud agent comment triggers and reasoning controls

GitHub added comment-triggered Copilot automations and per-task reasoning controls for Copilot cloud agent.

The AI Feed Desk

By The AI Feed Desk

A model selector dial routes three model chips to laptop, terminal, cloud agent, and mobile coding surfaces

GitHub rolls GPT-5.6 into Copilot across IDEs, CLI, agents, and mobile

GitHub is adding OpenAI's GPT-5.6 Sol, Terra, and Luna to Copilot across major developer surfaces, with enterprise and business access disabled by default.

The AI Feed Desk

By The AI Feed Desk

A coding-agent model picker routes a repository task to Grok 4.5 with policy and usage controls visible beside it

GitHub adds Grok 4.5 to Copilot's model picker

GitHub is rolling out xAI's Grok 4.5 across Copilot surfaces, with enterprise access controlled by an admin policy that is off by default.

The AI Feed Desk

By The AI Feed Desk

Developer work lanes compare coding, agent tasks, reasoning effort, and billing controls for Gemini 3.6 Flash in Copilot

Gemini 3.6 Flash rolls into GitHub Copilot

GitHub says Google's Gemini 3.6 Flash is rolling out in Copilot with configurable reasoning effort and parallel tool use.

The AI Feed Desk

By The AI Feed Desk