MiniMax-H3

by rioshiinaco.huggingface.rioshiina/minimax-h3

Multi-task video generator with dynamic, chainable workflows

  • Remote endpoint
  • 3 tools

Uptime

Checked  · every day

100%from 4 days of checks

Up without downtime on 4 of 4 days with data.

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

Response time

Median 1187 ms, slowest 5% 1265 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%

3 tools at the last answer.

Every day
DayResultChecksMedian
3 Nov (today)No downtime11196 ms
2 NovNo downtime1of 1985 ms
1 NovNo downtime1of 11253 ms
31 OctNo downtime21129 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 ~/.gemini/settings.json:

{
  "mcpServers": {
    "minimax-h3": {
      "url": "https://rioshiina-minimax-h3.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 MiniMax-H3 (`co.huggingface.rioshiina/minimax-h3`)

Its page: https://plug.directory/servers/co.huggingface.rioshiina/minimax-h3

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://rioshiina-minimax-h3.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse minimax-h3 https://rioshiina-minimax-h3.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": {
    "minimax-h3": {
      "url": "https://rioshiina-minimax-h3.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "minimax-h3": {
      "type": "sse",
      "url": "https://rioshiina-minimax-h3.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": {
    "minimax-h3": {
      "type": "sse",
      "url": "https://rioshiina-minimax-h3.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "minimax-h3"
    type: sse
    url: "https://rioshiina-minimax-h3.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": {
    "minimax-h3": {
      "url": "https://rioshiina-minimax-h3.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 3

  • MiniMax_H3_get_task_list [Recommended Flow Step 1] Get a list of supported video generation task types (t2va, i2va, flf2va, ref2va) along with their required/optional parameters and paste-and-run example_json_params.
  • MiniMax_H3_get_task_status Query the progress, status, and final generated results of an async video generation task.
  • MiniMax_H3_run [Recommended Flow Step 2] Unified video generation task execution interface (t2va, i2va, flf2va, ref2va). Accepts a JSON string or dict of parameters. REQUIRED PARAMETERS PER TASK TYPE: - t2va: task_type, prompt, width, height, duration - i2va: task_type, prompt, width, height, duration, first_frame_image - flf2va: task_type, prompt, width, height, duration, first_frame_image, last_frame_image - ref2va: task_type, prompt, width, height, duration GLOBAL OPTIONAL CONTROL PARAMETERS: - seed (int): Random seed (-1 for random, >=0 for deterministic reproducibility). Default: -1. - zero_gpu_duration (int): GPU quota allocation in seconds on HuggingFace ZeroGPU spaces (default: 120). REF2VA OPTIONAL MEDIA REFERENCES: - ref_image1..9: Image file path or URL - ref_video1..3: Video file path - ref_audio1..3: Audio file path

From Hugging Face Spaces. Report a problem