TabPFN-3.5, a Tabular Foundation Model for messy real-world tables

In the maker’s words

Releasing our MCP server that connects AI agents to TabPFN, a foundation model for tabular ML. Beta is open now. If you're building agents that work with tabular data (sales pipelines, customer data, inventory, financial records) you've probably hit this: agents spend tokens generating ML code that doesn't work, or produce unreliable results. TabPFN MCP gives LLMs 2 tools: fit_and_predict (fits a model and runs predictions) and predict (uses a previously fitted model). Your agents don't need to impute missing data, encode categorical features, or preprocess messy tables as TabPFN handles it natively. Available on ChatGPT, Claude, n8n and other major LLMs. Uses streamable HTTP for broad compatibility. Keeping the beta small to work closely with early users. If you're shipping with structured data, join here: https://priorlabs.ai/deployment/model-context-protocol Disclosure: I work at Prio…

Where people found it

• Hacker NewsShow HN: TabPFN-3.5, a Tabular Foundation Model for messy real-world tables10 points1 comments25 days ago
• Hacker NewsTabPFN-3: scaling foundation models for tabular data to 1M rows9 points0 comments2026-05-12
• Hacker NewsShow HN: TabPFN MCP, gives LLMs tools for predictions on tabular data (beta)11 points0 comments2026-02-05
• Hacker NewsShow HN: TabPFN Scaling Mode – Tabular Foundation Model on millions of rows5 points0 comments2025-12-03
• Hacker NewsShow HN: TabPFN-2.5 – SOTA foundation model for tabular data73 points13 comments2025-11-06
• Hacker NewsAI's Blind Spot: The Structured Data Challenge2 points0 comments2025-04-24