JetBrains plugin: support MCP tools in Copilot Chat

[Ginrey]

🏷️ Discussion Type

Bug

💬 Feature/Topic Area

JetBrains & Xcode

Body

Summary
GitHub Copilot is registered as an ACP (AI Coding Provider) agent in JetBrains IDEs, but unlike every other agent available in the same list (Claude, Gemini, Kimi, etc.), Copilot Chat does not receive MCP (Model Context Protocol) tool context from the JetBrains MCP server — even when the option "Pass IntelliJ MCP server" is enabled.

Environment

• JetBrains Rider (latest version)
• GitHub Copilot plugin (latest version, v1.478.0+)
• OS: macOS / Windows / Linux

Problem
JetBrains AI Assistant exposes a built-in MCP server that provides agents with powerful context tools:

• get_open_files — currently open editor files
• get_project_structure — full project file tree
• get_file_text — file contents
• run_configuration, list_problems, and others

All third-party ACP agents integrated via JetBrains AI Assistant (Claude Agent, Gemini, etc.) correctly receive these tools on every request, dramatically improving their ability to understand the codebase without manual context sharing.
GitHub Copilot does not. Despite appearing in the ACP agent list and having the MCP option available in settings, Copilot Chat operates in its own isolated chat environment (provided by the GitHub Copilot plugin itself) and does not proxy or consume MCP tools from JetBrains. The result is that Copilot Chat operates with significantly less context than competing agents running inside the same IDE on the same machine.

Impact
This creates a frustrating situation for Copilot subscribers:

1. You pay for a Copilot subscription expecting a capable coding assistant inside your IDE
2. Competing agents (some billed per-token, which gets expensive fast due to MCP context overhead) provide a meaningfully better in-IDE experience simply because they support MCP
3. Copilot users are forced to manually copy-paste file contents, use #file references, or switch tools — all workarounds that should be unnecessary

Expected Behavior
When a user opens Copilot Chat inside JetBrains Rider/IntelliJ and the "Pass IntelliJ MCP server" option is enabled, Copilot Chat should:

1. Connect to the local JetBrains MCP server
2. Expose its tools to the underlying model (currently claude-sonnet-4.6 / GPT-4.1 etc.)
3. Allow the model to call get_open_files, get_project_structure, and other tools autonomously during a conversation

Current Behavior
MCP tools are never passed to the model. Copilot Chat has no awareness of what files are open, what the project structure looks like, or what errors exist in the editor — unless the user manually provides this information.
Suggested Solution
The GitHub Copilot JetBrains plugin should implement an MCP client that connects to the JetBrains-provided MCP server (running on localhost) and forwards available tools into the Copilot Chat session, consistent with how other ACP agents already work today.
This is not a feature request for something novel — the infrastructure already exists in JetBrains. It just needs to be consumed by the Copilot plugin.

[github-actions[bot]]

💬 Your Product Feedback Has Been Submitted 🎉

Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users.

Here's what you can expect moving forward ⏩

• Your input will be carefully reviewed and cataloged by members of our product teams. 
  • Due to the high volume of submissions, we may not always be able to provide individual responses.
  • Rest assured, your feedback will help chart our course for product improvements.
• Other users may engage with your post, sharing their own perspectives or experiences. 
• GitHub staff may reach out for further clarification or insight. 
  • We may 'Answer' your discussion if there is a current solution, workaround, or roadmap/changelog post related to the feedback.

Where to look to see what's shipping 👀

• Read the Changelog for real-time updates on the latest GitHub features, enhancements, and calls for feedback.
• Explore our Product Roadmap, which details upcoming major releases and initiatives.

What you can do in the meantime 💻

• Upvote and comment on other user feedback Discussions that resonate with you.
• Add more information at any point! Useful details include: use cases, relevant labels, desired outcomes, and any accompanying screenshots.

As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities.

Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐