# ModelsLab v8

> ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.

- name: io.github.ModelsLab/modelslab-v8
- 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-v8
- tools: https://api.protogrid.dev/v1/servers/io.github.ModelsLab%2Fmodelslab-v8/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-v8": {
      "type": "http",
      "url": "https://modelslab.com/mcp/v8",
      "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-18d-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 4 of 8 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list-providers (destructiveHint, idempotentHint, openWorldHint); endpoint-details (destructiveHint, idempotentHint, openWorldHint); image-generation (readOnlyHint, destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 2,095 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: 8, about 2,095 tokens to load them all
- tool set hash: 3cb5e3a41bde109514db4cf4db629284
- tools last changed: 2026-10-05T13:54:18.779Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.ModelsLab/modelslab-v8.svg)](https://protogrid.dev/servers/io.github.ModelsLab/modelslab-v8)
- 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-v8/changes

## Remotes

- https://modelslab.com/mcp/v8 (streamable-http, auth oauth2, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `3d-generation`:     Generate 3D models using the ModelsLab V8 API.
    Supports any 3D endpoint available on the platform.
    Pass the `endpoint` slug and all required parameters for that endpoint.
    Returns a request ID that can be used with the fetch-generation tool to retrieve results.
    Use the list-models tool to find available model IDs.
- `audio-generation`:     Generate audio using the ModelsLab V8 API.
    Supports any audio endpoint (text-to-speech, speech-to-text, speech-to-speech, sound-generation, music-generation, song-extender, song-inpaint, dubbing, etc.).
    Pass the `endpoint` slug (e.g. "text-to-speech") and all required parameters for that endpoint.
    Returns a request ID that can be used with the fetch-generation tool to retrieve results.
    Use the list-models tool to find available model IDs.
- `endpoint-details`:     Search V8 endpoint configurations and retrieve their full parameter schemas plus all
    connected models that can be used with them.

    Use this tool before calling a generation tool so you know:
    - Exactly what `params` the endpoint expects (types, enums, defaults, required fields)
    - Which `model_id` values are valid for the endpoint

    Search modes:
    - Provide `category` + `endpoint` slug to look up a specific endpoint.
    - Provide `search` to find endpoints by name or description across all categories.
    - Combine both to narrow results to a category with a keyword search.

    Workflow:
    1. Call this tool to get the parameter schema and available model IDs.
    2. Pick a `model_id` from the `models` list in the response.
    3. Call the appropriate generation tool (`image-generation`, `video-generation`,
       `audio-generation`, `3d-generation`) with `model_id`, `endpoint`, and `params`.
- `fetch-generation`:     Check the status of a queued or processing generation request on the ModelsLab V8 API.

    Use this tool when a generation tool (image-generation, video-generation, audio-generation,
    3d-generation) returns a `status` of `"processing"` along with a numeric `id`.

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

    The response will contain:
    - `status`: "success", "processing", or "error"
    - `output`: array of URLs when status is "success"
- `image-generation`:     Generate images using the ModelsLab V8 API.
    Supports any image endpoint (text-to-image, image-to-image, inpaint, outpaint, fashion, virtual-try-on, etc.).
    Pass the `endpoint` slug (e.g. "text-to-image") and all required parameters for that endpoint.
    Returns a request ID that can be used with the fetch-generation tool to retrieve results.
    Use the list-models tool to find available model IDs.
- `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.
- `video-generation`:     Generate videos using the ModelsLab V8 API.
    Supports any video endpoint (text-to-video, image-to-video, video-to-video, lip-sync, motion-control, etc.).
    Pass the `endpoint` slug (e.g. "text-to-video") and all required parameters for that endpoint.
    Returns a request ID that can be used with the fetch-generation tool to retrieve results.
    Use the list-models tool to find available model IDs.