Conversation
Summary of ChangesHello @safaricd, 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 introduces comprehensive documentation for integrating various AI tools with the TabPFN Model Context Protocol (MCP) server. The new guide aims to streamline the process for users to connect their AI assistants, such as Claude, ChatGPT, Codex CLI, and Cursor, to leverage the TabPFN-2.5 model for instant predictions through a natural language interface, ensuring secure access via OAuth. Highlights
🧠 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
Activity
Using Gemini Code AssistThe 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
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 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
|
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds documentation for setting up and using the TabPFN MCP server. The new page provides clear instructions for various AI clients like Claude, ChatGPT, Codex CLI, and Cursor. My review includes a few minor suggestions to improve grammar, source code readability, and consistency in the provided shell commands. Overall, the documentation is well-written and easy to follow.
|
|
||
| ## What is TabPFN MCP? | ||
|
|
||
| TabPFN MCP is a remote MCP with OAuth that gives AI tools secure access TabPFN-2.5, our SOTA tabular foundation model. Our MCP server is available at: |
There was a problem hiding this comment.
There's a small grammatical error here. It should be 'secure access to TabPFN-2.5'.
TabPFN MCP is a remote MCP with OAuth that gives AI tools secure access to TabPFN-2.5, our SOTA tabular foundation model. Our MCP server is available at:
| It integrates with popular AI assistants like Claude, enabling you to run predictions using natural language. TabPFN MCP implements the latest | ||
| [MCP Authorization](https://modelcontextprotocol.io/specification/2025-06-18/basic/authorization) and [Streamable HTTP](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#streamable-http) specifications. |
There was a problem hiding this comment.
For better readability in the source file, it's best to avoid breaking a sentence across two lines like this. I suggest combining them into a single line.
It integrates with popular AI assistants like Claude, enabling you to run predictions using natural language. TabPFN MCP implements the latest [MCP Authorization](https://modelcontextprotocol.io/specification/2025-06-18/basic/authorization) and [Streamable HTTP](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#streamable-http) specifications.
|
|
||
| ```bash | ||
| # Install Codex | ||
| npm i -g @openai/codex |
There was a problem hiding this comment.
For consistency and clarity in documentation, it's better to use the full command npm install instead of the shorthand npm i. The 'Claude Code' section already uses npm install.
npm install -g @openai/codex
| description: "" | ||
| --- | ||
|
|
||
| Connect your AI tools to TabPFN using the [Model Context Protocol](https://modelcontextprotocol.io/) (MCP), |
There was a problem hiding this comment.
I would merge this sentence with the next (what is TabPFN MCP). First two sentences are almost the same right now
noahho
left a comment
noahho
left a comment
There was a problem hiding this comment.
Awesome! Just take a look at the Gemini & my comments
2 participants
This PR adds docs about using & setting up the TabPFN MCP server. The page was not added in the navigation tree yet because we want to keep access private.
A Loom demo recording will follow next week and will be part of a separate PR.