plug.directory
Add my server

AI Hub HF

by talent-active-devco.huggingface.talent-active-dev/ai-hub-hf

ترجمه JSON و رونویسی صوت با مدل<U+200C>های رایگان

Install in Claude Code Other clients
  • Remote endpoint
  • 10 tools

Uptime

Checked  · every day

99.2%from 4 days of checks

Up without downtime on 3 of 4 days with data; down 40 minutes in all, on 1 November.

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

Response time

Median 1177 ms, slowest 5% 1306 ms for the handshake and the tool list, over 30 days.

1500 ms750 ms0

How far each check got

  • Reached the address 92.3%
  • Completed the handshake 38.4%
  • Listed its tools 38.4%

10 tools at the last answer.

Every day
DayResultChecksMedian
3 Nov (today)No downtime11200 ms
2 NovNo downtime1of 11159 ms
1 NovDown 40 minutes9of 11235 ms
31 OctNo downtime21182 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

Run in a terminal:

claude mcp add --transport sse ai-hub-hf https://talent-active-dev-ai-hub-hf.hf.space/gradio_api/mcp/sse

Step by step for Claude Code

For agents: the install prompt

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

# Install the MCP server AI Hub HF (`co.huggingface.talent-active-dev/ai-hub-hf`)

Its page: https://plug.directory/servers/co.huggingface.talent-active-dev/ai-hub-hf

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://talent-active-dev-ai-hub-hf.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse ai-hub-hf https://talent-active-dev-ai-hub-hf.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": {
    "ai-hub-hf": {
      "url": "https://talent-active-dev-ai-hub-hf.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "ai-hub-hf": {
      "type": "sse",
      "url": "https://talent-active-dev-ai-hub-hf.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": {
    "ai-hub-hf": {
      "type": "sse",
      "url": "https://talent-active-dev-ai-hub-hf.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "ai-hub-hf"
    type: sse
    url: "https://talent-active-dev-ai-hub-hf.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": {
    "ai-hub-hf": {
      "url": "https://talent-active-dev-ai-hub-hf.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 10

  • ai_hub_hf_current_quota Report today's GPU consumption against the free daily allowance.
  • ai_hub_hf_delete_job_ui Delete a stored job from the UI.
  • ai_hub_hf_get_job_json Fetch a stored job by id or share link; returns the job as a JSON string. This is the shareable endpoint — the payload survives a page reload, so the original audio and translation can be replayed without spending GPU quota again.
  • ai_hub_hf_get_job_links Return the shareable page URL and JSON API URL for a stored job.
  • ai_hub_hf_get_job_srt Download the stored translation of a job as an SRT subtitle file.
  • ai_hub_hf_show_job Look up a stored job by id or share link and return it as JSON.
  • ai_hub_hf_show_job_on_enter Same lookup, wired to Enter-key submit (separate name so Gradio does not duplicate it).
  • ai_hub_hf_transcribe_audio Transcribe audio into segments with word-level timestamps. Returns {"segments", "words", "text", "job_id", "quota"}. The upload is kept under /data/jobs/<job_id>/ so get_job_json(job_id) can replay the result after a page reload without uploading again or spending more GPU quota. 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
  • ai_hub_hf_translate_json Translate segments from a JSON payload into Persian, preserving every timing field. Accepts either {"segments": [...]} or a bare list of segments, where each segment has at least "text" and ideally "start"/"end". Returns the same structure with the original text kept under "source_text" and the translation under "text".
  • ai_hub_hf_translate_json_1 Translate segments from a JSON payload into Persian, preserving every timing field. Accepts either {"segments": [...]} or a bare list of segments, where each segment has at least "text" and ideally "start"/"end". Returns the same structure with the original text kept under "source_text" and the translation under "text".

From Hugging Face Spaces. Report a problem