---
title: "GitHub's Copilot Code Review Now Reads Your Jira Tickets and Internal Docs"
subtitle: "GitHub Copilot code review now pulls context from MCP servers and custom agent skills, letting teams enforce their own standards on every PR automatically."
url: "https://alphasignal.ai/news/github-s-copilot-code-review-now-reads-your-jira-tickets-and-internal-docs"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "GitHub"
company_url: "https://alphasignal.ai/company/github"
published: "2026-06-12T17:55:33.000Z"
updated: "2026-06-12T22:18:01.929Z"
type: "News"
topics:
  - "Development"
  - "Api"
subtopics:
  - "Code Review"
upvotes: 294
read_time: "5 min"
source_url: "https://x.com/github/status/2065493219320713590"
comments: 0
---

# GitHub's Copilot Code Review Now Reads Your Jira Tickets and Internal Docs

> GitHub Copilot code review now pulls context from MCP servers and custom agent skills, letting teams enforce their own standards on every PR automatically.

Code review has always been a context problem. The reviewer staring at a diff often needs to know things that aren't in the diff: what the linked Jira ticket says, what the internal API contract requires, what the incident post-mortem recommended. Until now, Copilot's code review was blind to all of that. That just changed.

GitHub has shipped two public previews for [Copilot code review](https://github.blog/changelog/2026-06-02-shape-copilot-code-review-around-your-team/): support for custom agent skills and MCP server connections, plus a new "medium" analysis tier that routes complex pull requests to a higher-reasoning model. Both are available today for Copilot Pro, Pro+, Business, and Enterprise users.

## The context gap Copilot couldn't cross

The agentic shift in development has led to disjointed workflows, more context switching, and too much time spent reviewing agent-generated code. The core problem was always the same: a lot of what reviewers need to know lives in other tools, not in the diff itself.

Agent skills and MCP bring that context into Copilot's reviews, ensuring that reviews don't stall on questions already answered elsewhere. This means senior engineers stop being the bottleneck for consistency across repositories.

## Two new levers: skills and MCP

These two features are distinct but complementary. Here's what each one does:

- **Custom agent skills**: Custom agent skills invoke your team's internal tools and standards during a review, extending Copilot beyond its built-in analysis. You define them as markdown files in your repo.
- **MCP server connections**: Copilot code review can use MCP servers to pull context directly into the review from the third-party platforms and internal systems your team uses, including issue tracking, documentation, service catalogs, and incident tooling.

MCP (Model Context Protocol) is an open standard that lets AI models call out to external tools and data sources at runtime, like a plugin system for context. Think of it as giving the reviewer the ability to look things up mid-review rather than working only from memory.

The GitHub MCP server and Playwright MCP server are configured by default. Copilot cloud agent and Copilot code review do not currently support remote MCP servers that leverage OAuth for authentication and authorization -- so servers requiring OAuth flows are out for now.

One important detail: Copilot code review is more likely to use skills and MCP context when your repository or pull request gives clear signals, including review-focused skill directory names, custom instructions that reference MCP context, and pull request descriptions that include identifiers referencing configured MCP servers such as issue keys or incident IDs.

## A tiered model for review depth

Alongside the context upgrades, GitHub is introducing a two-tier review system. Copilot code review now offers a medium tier, which routes pull requests to a higher-reasoning model for better precision and recall.

- **Low**: Fast, cost-efficient. Good for docs, small repos, and low-risk changes.
- **Medium**: Routes to a more capable model. Better for complex logic, security-sensitive code, and cross-service changes. Consumes more AI Credits.

Admins can set guidelines for individual repositories to "low" or "medium," letting you assign lighter, cost-efficient models for low-risk code and save more robust model use for repos with higher impact.

## How to set it up

Getting MCP working for code review is a two-step repo-level config. Add your MCP server JSON under repository settings → **Copilot** → **MCP servers**, then store any required auth tokens under **Secrets and variables** → **Agents**. Notably, any existing MCP configurations for Copilot cloud agent will now apply to Copilot code review automatically.

For agent skills, the setup is file-based:

1. Create a `.github/skills` directory in your repo if one doesn't exist.
2. Under `.github/skills`, create a `code-review` or similarly named directory to ensure that Copilot code review will read and utilize the skill.
3. Create a `SKILL.md` file containing the relevant context and instructions you want Copilot code review to utilize.

Here's a minimal example of what a `SKILL.md` might look like for a team's API review standards:

```
# API Review Skill
When reviewing changes to files in /api or /routes:
- Verify all new endpoints are documented in /docs/api-spec.md
- Check that error responses follow the team's standard error schema
- Flag any endpoint that does not validate input with our shared validator utility
- Reference the linked Jira ticket for acceptance criteria
```

To verify what context Copilot actually used, open the linked review session from the pull request timeline, then check the session logs to see which MCP servers and tools were called.

## Where it still falls short

This is a public preview, and the caveats matter. Copilot is not guaranteed to spot all problems or issues in a pull request. Sometimes it will make mistakes. Always validate Copilot's feedback carefully. Supplement Copilot's feedback with a human review.

The MCP integration is also not unconditional. Copilot won't call MCP tools on every review automatically -- it needs clear signals from the PR description or skill configuration to know when external context is relevant. Teams that don't structure their PRs with issue keys or explicit instructions may see inconsistent MCP usage.

## Practical use-cases worth trying

- **Jira/Linear integration**: Link a ticket ID in your PR description and have Copilot check the diff against the acceptance criteria in the issue.
- **Internal API contracts**: Use a skill to load your service catalog and flag changes that break downstream consumers.
- **Security checklists**: Point Copilot at your org's security runbook so it applies the same checks a senior engineer would.
- **Incident-aware reviews**: Connect an incident tooling MCP server so Copilot knows which systems are currently fragile and flags risky changes accordingly.
- **Tiered repo strategy**: Set core services to "medium" review depth and internal tooling repos to "low" to manage AI credit spend.

The real unlock here isn't any single feature -- it's that platform teams can now invest once in a shared MCP configuration and get consistent, context-aware review behavior across every repo in the organization, without asking senior engineers to repeat themselves on every PR.

## Sources

- [X post by @github](https://x.com/github/status/2065493219320713590)
- [Shape Copilot code review around your team - GitHub Changelog](https://github.blog/changelog/2026-06-02-shape-copilot-code-review-around-your-team/)
- [About GitHub Copilot code review - GitHub Docs](https://docs.github.com/en/copilot/concepts/agents/code-review)
- [Using GitHub Copilot code review - GitHub Docs](https://docs.github.com/copilot/using-github-copilot/code-review/using-copilot-code-review)
- [GitHub Copilot app: The agent-native desktop experience - The GitHub Blog](https://github.blog/news-insights/product-news/github-copilot-app-the-agent-native-desktop-experience/)
- [Model Context Protocol (MCP) and GitHub Copilot cloud agent - GitHub Docs](https://docs.github.com/en/copilot/concepts/agents/coding-agent/mcp-and-coding-agent)