TabPFN-3.5 — Tabular Foundation Model

by hugging-appsco.huggingface.hugging-apps/tabpfn-3-5-demo

Train a tabular foundation model in one forward pass

  • Remote endpoint
  • 6 tools

Uptime

Checked  · every day

100%from 4 days of checks

Up without downtime on 3 of 3 days with data.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

Response time

Median 1137 ms, slowest 5% 1213 ms for the handshake and the tool list, over 30 days.

1500 ms750 ms0

How far each check got

  • Reached the address 100%
  • Completed the handshake 100%
  • Listed its tools 100%

6 tools at the last answer.

Every day
DayResultChecksMedian
3 Nov (today)No verdict yet0–
2 NovNo downtime1of 11213 ms
1 NovNo downtime1of 11198 ms
31 OctNo downtime21121 ms

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Paste into Settings › Connectors › Add custom connector:

https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse
For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server TabPFN-3.5 — Tabular Foundation Model (`co.huggingface.hugging-apps/tabpfn-3-5-demo`)

Its page: https://plug.directory/servers/co.huggingface.hugging-apps/tabpfn-3-5-demo

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse tabpfn-3-5-demo https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse
```

## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project

```json
{
  "mcpServers": {
    "tabpfn-3-5-demo": {
      "url": "https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "tabpfn-3-5-demo": {
      "type": "sse",
      "url": "https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Zed

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Cline, AnythingLLM, Augment Code

Merge into the place for the person's client:

- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)

```json
{
  "mcpServers": {
    "tabpfn-3-5-demo": {
      "type": "sse",
      "url": "https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "tabpfn-3-5-demo"
    type: sse
    url: "https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse"
```

## Goose

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Codex

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "tabpfn-3-5-demo": {
      "url": "https://hugging-apps-tabpfn-3-5-demo.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

Tools 6

  • tabpfn_3_5_demo_on_dataset_change Update the target-column dropdown after the data source changes. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • tabpfn_3_5_demo_on_dataset_change_1 Update the target-column dropdown after the data source changes. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • tabpfn_3_5_demo_peek_rows Show the first 5 rows of the selected dataset. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • tabpfn_3_5_demo_peek_rows_1 Show the first 5 rows of the selected dataset. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • tabpfn_3_5_demo_peek_rows_2 Show the first 5 rows of the selected dataset. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • tabpfn_3_5_demo_run_tabpfn Train TabPFN-3.5 on your tabular data and evaluate on a held-out split. Upload a CSV or select a built-in dataset, pick the target column, and TabPFN-3.5 fits in a single forward pass - no gradient descent and no hyperparameters. Returns test-split predictions with per-class probabilities (classification) or predicted values (regression), a confusion matrix (classification), and headline metrics. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

From Hugging Face Spaces. Report a problem