TabPFN MCP, gives LLMs tools for predictions on tabular data (beta)

TabPFN MCP is a Model Context Protocol (MCP) server that plugs state-of-the-art TabPFN tabular prediction into any MCP-enabled LLM. Instead of manually exporting CSVs, tuning models, and wiring up APIs, your AI assistant can call TabPFN directly to train and predict on structured data within a single conversation. TabPFN is a pretrained transformer-based model for tabular data that delivers strong performance out of the box, often rivaling traditional AutoML workflows with a fraction of the latency and setup. With TabPFN MCP, LLMs gain a dedicated tool for classification and regression on tables, enabling workflows like churn prediction, lead scoring, risk modeling, or experiment analysis to run interactively. The MCP interface cleanly separates data access from model logic, so you keep full control over how data is loaded, filtered, and governed. Designed for developers, data practitioners, and AI product teams, TabPFN MCP fits neatly into your existing MCP ecosystem, works alongside other tools, and can be deployed wherever your LLM runs. It’s currently in beta, making it ideal for early adopters who want to prototype and iterate quickly on AI copilots that understand and reason over tabular data, without rebuilding an ML stack from scratch.

PricingUnknown

views

favorites

Features

MCP-native tabular prediction tools
Pretrained TabPFN for tables
Interactive classification and regression

Use Cases

Sales teams let an MCP-enabled LLM score leads and predict conversion probability directly from CRM tables, without exporting data to external ML services.
Data analysts query experiment logs via the LLM and use TabPFN MCP to model outcomes, compare variants, and surface drivers of performance on the fly.
Risk teams run quick classification models over transaction tables to flag high-risk entries, testing new rules and features conversationally with the assistant.
Product managers explore cohort behavior by having the LLM build regression models on usage metrics, forecasting impact of feature changes in real time.
Developers prototype internal AI tools where the assistant can join, filter, and then predict on operational data stored in databases or data warehouses.

TabPFN MCP, gives LLMs tools for predictions on tabular data (beta)

Features

Use Cases

Frequently Asked Questions

What is TabPFN MCP and how does it work with LLMs?

What kinds of tabular tasks can TabPFN MCP handle?

Do I need ML expertise or hyperparameter tuning to use it?

How is my data handled and where does it live?

Is TabPFN MCP free to use and production-ready?

User Reviews