MCP docs

[safaricd]

This PR restructures the MCP docs and includes additional content ahead of the launch.

[chatgpt-codex-connector]

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

[gemini-code-assist]

Summary of Changes

Hello, 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 documentation for the Model Context Protocol (MCP) by introducing a dedicated 'Agentic' section. It provides users with comprehensive guides on setting up TabPFN MCP with various AI clients, detailed explanations of the available tools, and a practical tutorial for a churn prediction use case with Databricks. The changes aim to improve the discoverability and usability of MCP-related information, supporting users in leveraging TabPFN-2.5 with AI tools.

Highlights

• New Agentic Documentation: Introduced a new 'Agentic' section in the documentation, including an overview of the Model Context Protocol (MCP), a setup guide for various AI clients, and detailed tool usage.
• Comprehensive Setup Guide: Provided step-by-step instructions for integrating TabPFN MCP with popular AI clients such as Claude Code, Claude.ai, ChatGPT, Codex CLI, Cursor, and n8n.
• Detailed Tool Reference: Documented the TabPFN MCP server's tools, including upload_dataset, fit_and_predict_from_dataset, predict_from_dataset, fit_and_predict_inline, and predict, with their required and optional parameters and return types.
• Databricks Tutorial: Added a new tutorial demonstrating how to connect Databricks Delta tables to TabPFN's MCP server to run a churn prediction pipeline using an AI agent.
• Documentation Restructuring: Refactored and moved existing MCP documentation from integrations/mcp.mdx into the new agentic directory for better organization and clarity.

🧠 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.

Changelog

• agentic/mcp.mdx
  • Added introductory documentation for the Model Context Protocol (MCP).
• agentic/setup-guide.mdx
  • Added a comprehensive guide for setting up TabPFN MCP with various AI clients.
• agentic/tool-use.mdx
  • Added detailed documentation for the TabPFN MCP server's exposed tools.
• agentic/tutorials/databricks.mdx
  • Added a tutorial demonstrating a churn prediction pipeline using Databricks and an AI agent.
• docs.json
  • Updated the documentation navigation to include the new agentic content.
• integrations/mcp.mdx
  • Removed the previous Model Context Protocol documentation.

Activity

• The author restructured the MCP documentation and added new content in preparation for a launch.

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 significantly restructures the MCP documentation by splitting it into dedicated files for introduction, setup, and tool usage, and adds a new tutorial for Databricks. However, the tutorial script in agentic/tutorials/databricks.mdx contains security vulnerabilities where AI agent tools lack validation for file paths and URLs, potentially enabling prompt injection for path traversal, data exfiltration, or SSRF. These security concerns should be addressed to promote secure coding practices. Additionally, the review includes suggestions to enhance clarity and completeness in the new documentation files and to improve the robustness and resource management of the example Python script in the Databricks tutorial.