Qwen3-4B Dijkstra Unlearn & Reinvent

by hugging-appsco.huggingface.hugging-apps/qwen3-4b-thinking-2507-dijkstra-unlearn

Unlearned on Dijkstra — can it reinvent the algorithm?

  • Remote endpoint
  • 7 tools
  • APACHE-2.0

Uptime

Checked  · every day

99.82%from 5 days of checks

Up without downtime on 4 of 5 days with data; down 10 minutes in all, on 1 November.

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

Response time

Median 1232 ms, slowest 5% 1336 ms for the handshake and the tool list, over 30 days.

1500 ms750 ms0

How far each check got

  • Reached the address 85.7%
  • Completed the handshake 71.4%
  • Listed its tools 71.4%

7 tools at the last answer.

Every day
DayResultChecksMedian
4 Nov (today)No downtime11140 ms
3 NovNo downtime1of 11159 ms
2 NovNo downtime1of 11257 ms
1 NovDown 10 minutes3of 11244 ms
31 OctNo downtime11094 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

Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):

{
  "mcpServers": {
    "qwen3-4b-thinking-2507-dijkstra-unlearn": {
      "url": "https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.hf.space/gradio_api/mcp/sse"
    }
  }
}

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

For agents: the install prompt

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

# Install the MCP server Qwen3-4B Dijkstra Unlearn & Reinvent (`co.huggingface.hugging-apps/qwen3-4b-thinking-2507-dijkstra-unlearn`)

Its page: https://plug.directory/servers/co.huggingface.hugging-apps/qwen3-4b-thinking-2507-dijkstra-unlearn

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-qwen3-4b-thinking-2507-dijkstra-unlearn.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse qwen3-4b-thinking-2507-dijkstra-unlearn https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.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": {
    "qwen3-4b-thinking-2507-dijkstra-unlearn": {
      "url": "https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "qwen3-4b-thinking-2507-dijkstra-unlearn": {
      "type": "sse",
      "url": "https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.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": {
    "qwen3-4b-thinking-2507-dijkstra-unlearn": {
      "type": "sse",
      "url": "https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "qwen3-4b-thinking-2507-dijkstra-unlearn"
    type: sse
    url: "https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.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": {
    "qwen3-4b-thinking-2507-dijkstra-unlearn": {
      "url": "https://hugging-apps-qwen3-4b-thinking-2507-dijkstra-unlearn.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 7

  • qwen3_4b_thinking_2507_dijkstra_unlearn__add_user Echo the user message instantly; clear the box (the message lives in history). 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
  • qwen3_4b_thinking_2507_dijkstra_unlearn__add_user_1 Echo the user message instantly; clear the box (the message lives in history). 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
  • qwen3_4b_thinking_2507_dijkstra_unlearn__lambda_
  • qwen3_4b_thinking_2507_dijkstra_unlearn__preview
  • qwen3_4b_thinking_2507_dijkstra_unlearn_chat Chat with the Dijkstra-unlearned model and run the paper's forbidden-string probe. The new user message is the last user turn of `history` (the UI chain appends it before this step runs). Yields (updated_history, leak_badge) while streaming. 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
  • qwen3_4b_thinking_2507_dijkstra_unlearn_chat_1 Chat with the Dijkstra-unlearned model and run the paper's forbidden-string probe. The new user message is the last user turn of `history` (the UI chain appends it before this step runs). Yields (updated_history, leak_badge) while streaming. 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
  • qwen3_4b_thinking_2507_dijkstra_unlearn_run_challenge Run one Dijkstra-reinvention attempt and grade it on the paper's test cases.

From Hugging Face Spaces. Report a problem