MCP server
TabPFN-3.5 — Tabular Foundation Model
hf/hugging-apps/tabpfn-3-5-demo
Checked 28 Oct 2026, 09:04 UTC · Hugging Face reports it running
Train a tabular foundation model in one forward pass
Working at last check
https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Working at last check
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
- Last checked
- 28 Oct 2026, 09:04 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.
Claude Code
claude mcp add --transport http tabpfn-3-5-demo https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/
Claude Desktop
Settings → Connectors → Add custom connector, and paste the URL.
Codex (config.toml)
[mcp_servers.tabpfn-3-5-demo] url = "https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/"
Gemini CLI
{"mcpServers":{"tabpfn-3-5-demo":{"httpUrl":"https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/"}}}
Cursor
{"mcpServers":{"tabpfn-3-5-demo":{"url":"https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/"}}}
VS Code
{"servers":{"tabpfn-3-5-demo":{"type":"http","url":"https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/"}}}
Antigravity
agy mcp add tabpfn-3-5-demo https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/
ChatGPT
Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.
OpenAI API (Responses tools)
{"type":"mcp","server_label":"tabpfn-3-5-demo","server_url":"https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/","require_approval":"always"}
Grok (xAI API tools)
{"type":"mcp","server_label":"tabpfn-3-5-demo","server_url":"https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/"}
Related MCP servers
- EXAONE Tabular
In-context tabular prediction from a CSV - Causilo
In-context tabular prediction from a CSV - LimiX-2 Tabular In-Context Learning
In-context classification, regression & imputation on tables - Laya Multilingual Demo
System 1 decisions in 100+ languages, one forward pass - GLiNER2.5-Decide — Any Label Set, One Forward Pass
One checkpoint, any label set, instant text decisions - Kev Demo (CPU)
tiny decision models — one forward pass, no text generated - this-that-model-1.0
One forward pass, no decoding: calibrated typed decisions - Laya Multilingual
Typed decisions in 100+ languages, one forward pass
Badge for your README
[](https://aptlynx.net/servers/hf/hugging-apps/tabpfn-3-5-demo)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents