feat(py): add mcp sample

[MengqinShen]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @MengqinShen, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the Genkit Python framework's integration with the Model Context Protocol (MCP) by introducing a new, detailed sample application. It also includes crucial updates to the MCP client for more robust asynchronous resource management and modifies the Genkit core to support asynchronous action resolution from plugins. These changes collectively improve the stability, flexibility, and demonstrability of MCP plugin interactions within Genkit, particularly for dynamic tool and resource handling.

Highlights

• New MCP Sample Application: A comprehensive new sample application for the Model Context Protocol (MCP) has been added, demonstrating various client functionalities including git operations, file system interactions, and dynamic tool/resource management. This sample includes both client and server examples.
• MCP Client Refactoring for Async Operations: The MCP client has been significantly refactored to leverage AsyncExitStack for robust asynchronous resource management, simplifying connection and closure logic. It also introduces new methods for dynamically listing active tools and resources.
• Genkit Registry Asynchronous Action Support: The core Genkit registry now supports asynchronous action listing, allowing plugins to return awaitable objects when resolving actions. This enhances flexibility for plugins that need to perform async operations to list their capabilities.
• Improved Tool Naming Convention: The Google GenAI plugin now automatically replaces '/' characters with '__' in tool names during registration. This prevents potential issues with path-like tool names in various systems.
• Plugin Initialization Flow Enhancement: The plugin initialization process has been refined to ensure plugins are registered with the AI registry before their initialize method is called, and a check is added to ensure the initialize method exists.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new MCP sample and includes several refactorings to support it. The changes are generally positive, improving robustness with AsyncExitStack for resource management and making core components like list_actions asynchronous. I've found one critical issue that will cause a NameError and a couple of medium-severity suggestions to improve code clarity and reduce duplication. Overall, this is a solid contribution that adds valuable examples and enhances the framework's capabilities.