# ModelsLab

> Generate images, video, speech and music, and run LLM chat, across 10,000+ models on ModelsLab.

- name: io.github.ModelsLab/modelslab
- version: 1.0.0
- connection class: R2 (oauth_consent_once)
- trust: 93/100 flags: duplicate-repo
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.ModelsLab%2Fmodelslab
- tools: https://api.protogrid.dev/v1/servers/io.github.ModelsLab%2Fmodelslab/tools

**An agent can connect after a one-time OAuth consent by a human.** Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "modelslab": {
      "type": "http",
      "url": "https://modelslab.com/mcp/v7",
      "headers": {
        "Authorization": "Bearer ${api_key}"
      }
    }
  }
}
```

Placeholders to fill: `${api_key}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-17d-ago -duplicate-repo(3 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: 83 (weight 15)

- pass `auth.prm`: Protected Resource Metadata (RFC 9728) published
- pass `auth.as_metadata`: authorization server metadata reachable
- warn `auth.cimd`: only Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 6 of 23 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: fetch-image (destructiveHint, idempotentHint, openWorldHint); text-to-video (readOnlyHint, destructiveHint, idempotentHint); motion-control (readOnlyHint, destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 5,894 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 23, about 5,894 tokens to load them all
- tool set hash: e8b035ba099de7bf9a11e3762dae3d91
- tools last changed: 2026-10-05T10:51:45.857Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.ModelsLab/modelslab.svg)](https://protogrid.dev/servers/io.github.ModelsLab/modelslab)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-05 `list-models` changed (inputSchema)
- 2026-10-02 `list-models` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.ModelsLab%2Fmodelslab/changes

## Remotes

- https://modelslab.com/mcp/v7 (streamable-http, auth oauth2, reachable true, uptime30d 1)

## Packages

_none_

## Tools (23)

- `chat-completion`:     Chat with AI language models.
    Send messages to an LLM and receive AI-generated responses.
    Supports various models and configuration options.
    A message may carry a PDF as a {"type":"file","file":{"filename":...,"file_data":"data:application/pdf;base64,..."}} content part.
- `dubbing`:     Create dubbed audio content.
    Takes a video and translates/dubs the audio from one language to another.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `fetch-audio`:     Retrieve the status and results of an audio generation request.
    Use the request ID returned from text-to-speech, speech-to-text, music-generation, and other audio tools.
- `fetch-generation`:     Check the status of a queued or processing generation request on the ModelsLab V7 API.

    Use this tool when a generation tool returns a `status` of `"processing"`, and call it again
    while the status stays `"processing"`. Image jobs usually finish in seconds; video and music
    jobs can take several minutes, so tell the user the job is still running if it has not
    finished after a few polls.

    Pass the `id` from the original generation response and the `type` matching the category
    of the original request (e.g. "images" for text-to-image, image-to-image, or inpaint-image).

    The response will contain:
    - `status`: "success", "processing", or "error"
    - `output`: array of URLs when status is "success"
- `fetch-image`:     Retrieve the status and results of an image generation request.
    Use the request ID returned from text-to-image, image-to-image, or inpaint-image tools.
- `fetch-video`:     Retrieve the status and results of a video generation request.
    Use the request ID returned from text-to-video, image-to-video, video-to-video, lip-sync, or motion-control tools.
- `image-to-image`:     Transform existing images based on text prompts.
    Takes an input image and modifies it according to the provided prompt.
    Returns a request ID that can be used with fetch-image to retrieve results.
- `image-to-video`:     Animate static images into videos.
    Takes input image(s) and creates a video based on the prompt.
    Returns a request ID that can be used with fetch-video to retrieve results.
- `inpaint-image`:     Edit specific areas of images using masks.
    Provide an image, a mask indicating the area to edit, and a prompt describing the desired changes.
    Returns a request ID that can be used with fetch-image to retrieve results.
- `lip-sync`:     Sync video with audio for lip movements.
    Takes a video and audio file and syncs the lip movements to match the audio.
    Returns a request ID that can be used with fetch-video to retrieve results.
- `list-models`:     List available AI models on the ModelsLab platform.
    Filter by category (imagen, video, audio, llm, 3d), provider, tags, and more.
    Returns model IDs that can be used with generation tools.
- `list-providers`:     List all available model providers on the ModelsLab platform.
    Returns provider names with model counts for each.
    Use provider names to filter models in the list-models tool.
- `motion-control`:     Control motion in video generation.
    Uses an image and video to create motion-controlled output.
    Returns a request ID that can be used with fetch-video to retrieve results.
- `music-generation`:     Create music from text prompts.
    Generates original music based on your description, optional tags, and lyrics.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `song-extender`:     Extend existing music tracks.
    Takes an existing audio file and extends it from either the beginning or end.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `song-inpaint`:     Edit specific sections of songs.
    Takes an audio file and regenerates a specific section defined by start and end times.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `sound-generation`:     Generate sound effects from text descriptions.
    Creates audio sound effects based on your prompt.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `speech-to-speech`:     Voice conversion and transformation.
    Takes an audio file and converts it to a different voice.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `speech-to-text`:     Transcribe audio to text.
    Takes an audio file and converts it to text transcription.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `text-to-image`:     Generate images from text prompts using AI models.
    Returns a request ID that can be used with fetch-image to retrieve results.
    Supports various AI image generation models.
- `text-to-speech`:     Convert text to natural speech audio.
    Takes text and generates realistic speech using the specified voice.
    Returns a request ID that can be used with fetch-audio to retrieve results.
- `text-to-video`:     Generate videos from text descriptions.
    Creates AI-generated videos based on your text prompt.
    Returns a request ID that can be used with fetch-video to retrieve results.
- `video-to-video`:     Transform existing videos with AI.
    Takes input video(s) and modifies them based on the prompt.
    Returns a request ID that can be used with fetch-video to retrieve results.