# Extending AI Agents: A live demo of the GitHub MCP Server Source: https://www.youtube.com/watch?v=LwqUp4Dc1mQ Recap page: https://rapidrecap.app/video/LwqUp4Dc1mQ Generated: 2025-11-30T15:32:53.817+00:00 --- ## Quick Overview The GitHub MCP Server enables AI agents to interact with the outside world by providing standardized access to context like file systems, GitHub repositories, and external web resources, as demonstrated by listing repository issues and fetching an image file via a prompt. **Key Points:** - The GitHub MCP Server (Model Context Protocol) allows AI agents to interact with external resources like files, APIs, and databases, transforming how humans and agents interact with code. - The server was created by Anthropic and launched in November, quickly gaining over 24,000 stars on GitHub, making it one of the most popular open-source projects on the platform. - The demonstration showed the agent successfully listing 10 open issues from the 'SamMorrowDrums/universe-optimistic' repository and identifying issue #19 as suitable for Copilot. - The agent successfully executed a tool command to fetch the 'example_doge.png' file from the repository and displayed the image content, demonstrating rich media handling. - The GitHub MCP Server offers enterprise features like Secret Scanning push protection, read-only mode for sensitive workloads, and Enterprise support for GHEC/GHES. - Users can explore the available tools and configure their MCP server via the MCP Registry at github.com/mcp. ![Screenshot at 00:07: The title slide introduces the presentation topic: "Extending AI Agents: A Live Demo of the GitHub MCP Server," featuring presenters Sam Morrow and Toby Padilla.](https://ss.rapidrecap.app/screens/LwqUp4Dc1mQ/00-00-07.png) **Context:** Sam Morrow (Senior Software Engineer at GitHub) and Toby Padilla (Principal Product Manager at GitHub) presented a live demonstration of the GitHub MCP Server at GitHub Universe 2025. The presentation focused on how this server extends AI agents by giving them standardized access to external context and tools, improving their capabilities beyond their initial training data. ## Detailed Analysis The presentation introduced the GitHub MCP (Model Context Protocol) Server, a tool designed to allow AI agents to interact with the outside world—specifically GitHub resources, files, and APIs—by creating a standardized protocol for context access. Sam Morrow and Toby Padilla demonstrated its capabilities, noting that the project, created by Anthropic, achieved massive popularity quickly, surpassing 24,000 stars. The demo highlighted the agent's ability to execute complex, multi-step actions: first, the agent analyzed the last 10 issues in the 'SamMorrowDrums/universe-optimistic' repository, identified issue #19 as suitable for Copilot, and assigned it. Then, in a separate demonstration, the agent successfully executed a 'Get File' tool command to fetch an image ('example_doge.png') from the repository and displayed the image (a Doge meme) directly in the interface, confirming its capability to handle rich media context. The presenters also highlighted enterprise features, including Secret Scanning push protection, read-only mode for sensitive workloads, and support for GHEC/GHES via the local MCP server. The audience was encouraged to try the technology themselves at github.com/mcp. ### Introduction and Context - Sam Morrow and Toby Padilla welcome the audience - Toby Padilla explains MCP is about 11 months old and created by Anthropic - The original MCP server was written in TypeScript and rewriten to Rust. ### What is MCP? - MCP (Model Context Protocol) is a way for AI to interact with the outside world, fetching context not in its training data, such as file systems or GitHub repos - It allows agents to create side effects like creating files or designs. ### GitHub MCP Server Success - The server gained over 24,000 stars quickly, becoming one of the most popular open-source projects on GitHub - It has more support for the MCP protocol than any other server, including features for self-publishing. ### Live Demo - Issue Triage - The agent analyzed the last 10 issues in the 'SamMorrowDrums/universe-optimistic' repo to determine suitability for Copilot - It confidently assigned issue #19, 'Implement Animal Voting and Rating System,' to Copilot. ### Live Demo - File Fetching - The agent successfully fetched and displayed an image file ('example_doge.png') from the repository, demonstrating rich media context handling. ### GitHub MCP Server Features - Includes Secret Scanning push protection, Read-only mode, Enterprise support for GHEC/GHES, and is used by Copilot coding agent by default. ### Call to Action - Users can try the MCP Registry at github.com/mcp to explore various community-contributed servers. ![Screenshot at 00:03: The opening slide for GitHub Universe 25, setting the context for the presentation.](https://ss.rapidrecap.app/screens/LwqUp4Dc1mQ/00-00-03.png) ![Screenshot at 00:07: The title slide for the talk, featuring presenters Sam Morrow and Toby Padilla.](https://ss.rapidrecap.app/screens/LwqUp4Dc1mQ/00-00-07.png) ![Screenshot at 00:45: The presentation agenda outlining the talk structure: Quick Intro, Setup/Install, Explore GitHub Issues via MCP, and Further use cases.](https://ss.rapidrecap.app/screens/LwqUp4Dc1mQ/00-00-45.png) ![Screenshot at 01:48: A slide asking "What is MCP? \(Model Context Protocol\)" as Toby Padilla begins the explanation.](https://ss.rapidrecap.app/screens/LwqUp4Dc1mQ/00-01-48.png) ![Screenshot at 03:25: The screen displays the MCP Registry homepage, showing various available MCP servers like Markdown, Context7, and GitHub.](https://ss.rapidrecap.app/screens/LwqUp4Dc1mQ/00-03-25.png)