Server definition

Hash: sha256:67a8c651f8973497f824ab68ea8fd2199abe84d62314ebb54291bf9e3e501585
What it is: What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{
  "instructions": "    ModelsLab V8 API Server provides unified AI-powered generation capabilities:\n\n    ## Models\n    - `list-models`: Browse and search available AI models on the platform\n    - `list-providers`: List all model providers with model counts\n\n    ## Endpoint Discovery (use this first)\n    - `endpoint-details`: Search endpoint configurations and get the full parameter schema\n      plus all connected model IDs for any V8 endpoint. Supports keyword search and\n      category/slug filtering. Always call this before generating to know the correct params.\n\n    ## Image Generation (`image-generation`)\n    A unified gateway for all image operations. Pass `model_id`, `endpoint` (slug), and `params`.\n    Available endpoints: `text-to-image`, `image-to-image`, `outpaint`, `fashion`, `virtual-try-on`\n\n    ## Video Generation (`video-generation`)\n    A unified gateway for all video operations. Pass `model_id`, `endpoint` (slug), and `params`.\n    Available endpoints: `text-to-video`\n\n    ## Audio Generation (`audio-generation`)\n    A unified gateway for all audio operations. Pass `model_id`, `endpoint` (slug), and `params`.\n    Available endpoints: `text-to-speech`, `music-generation`\n\n    ## 3D Generation (`3d-generation`)\n    A unified gateway for all 3D operations. Pass `model_id`, `endpoint` (slug), and `params`.\n\n    Recommended workflow:\n    1. Call `endpoint-details` with the category and endpoint slug to get the parameter schema and valid model IDs.\n    2. Call the appropriate generation tool with `model_id`, `endpoint`, and `params`.\n    3. If the response has `status: \"processing\"`, call `fetch-generation` with the returned `id` and `type` to poll for results.",
  "tools": [
    {
      "description": "    Generate 3D models using the ModelsLab V8 API.\n    Supports any 3D endpoint available on the platform.\n    Pass the `endpoint` slug and all required parameters for that endpoint.\n    Returns a request ID that can be used with the fetch-generation tool to retrieve results.\n    Use the list-models tool to find available model IDs.",
      "inputSchema": {
        "properties": {
          "endpoint": {
            "description": "The 3D operation slug.",
            "enum": [],
            "type": "string"
          },
          "model_id": {
            "description": "The model ID to use for 3D generation.",
            "type": "string"
          },
          "params": {
            "description": "Additional parameters for the endpoint (e.g. prompt, init_image, webhook, track_id).",
            "type": "object"
          }
        },
        "required": [
          "model_id",
          "endpoint"
        ],
        "type": "object"
      },
      "name": "3d-generation",
      "outputSchema": null
    },
    {
      "description": "    Generate audio using the ModelsLab V8 API.\n    Supports any audio endpoint (text-to-speech, speech-to-text, speech-to-speech, sound-generation, music-generation, song-extender, song-inpaint, dubbing, etc.).\n    Pass the `endpoint` slug (e.g. \"text-to-speech\") and all required parameters for that endpoint.\n    Returns a request ID that can be used with the fetch-generation tool to retrieve results.\n    Use the list-models tool to find available model IDs.",
      "inputSchema": {
        "properties": {
          "endpoint": {
            "description": "The audio operation slug.",
            "enum": [],
            "type": "string"
          },
          "model_id": {
            "description": "The model ID to use for audio generation.",
            "type": "string"
          },
          "params": {
            "description": "Additional parameters for the endpoint (e.g. prompt, voice_id, init_audio, init_video, tags, lyrics, source_lang, output_lang, webhook, track_id).",
            "type": "object"
          }
        },
        "required": [
          "model_id",
          "endpoint"
        ],
        "type": "object"
      },
      "name": "audio-generation",
      "outputSchema": null
    },
    {
      "description": "    Search V8 endpoint configurations and retrieve their full parameter schemas plus all\n    connected models that can be used with them.\n\n    Use this tool before calling a generation tool so you know:\n    - Exactly what `params` the endpoint expects (types, enums, defaults, required fields)\n    - Which `model_id` values are valid for the endpoint\n\n    Search modes:\n    - Provide `category` + `endpoint` slug to look up a specific endpoint.\n    - Provide `search` to find endpoints by name or description across all categories.\n    - Combine both to narrow results to a category with a keyword search.\n\n    Workflow:\n    1. Call this tool to get the parameter schema and available model IDs.\n    2. Pick a `model_id` from the `models` list in the response.\n    3. Call the appropriate generation tool (`image-generation`, `video-generation`,\n       `audio-generation`, `3d-generation`) with `model_id`, `endpoint`, and `params`.",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Narrow results to a V8 category: \"images\", \"videos\", \"audios\", or \"3ds\". Optional — omit to search all categories.",
            "enum": [
              "images",
              "videos",
              "audios",
              "3ds"
            ],
            "type": "string"
          },
          "endpoint": {
            "description": "The endpoint slug to look up (e.g. \"text-to-image\", \"text-to-speech\"). Optional — omit to return all endpoints in the category.",
            "enum": [
              "flux-headshot"
            ],
            "type": "string"
          },
          "limit": {
            "default": 10,
            "description": "Maximum number of endpoint configurations to return (1–20). Defaults to 10.",
            "type": "integer"
          },
          "model_limit": {
            "default": 5,
            "description": "Maximum number of connected models to return per endpoint, sorted by popularity (1–20). Defaults to 5.",
            "type": "integer"
          },
          "search": {
            "description": "Keyword to search endpoint names and descriptions (e.g. \"speech\", \"image turbo\").",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "endpoint-details",
      "outputSchema": null
    },
    {
      "description": "    Check the status of a queued or processing generation request on the ModelsLab V8 API.\n\n    Use this tool when a generation tool (image-generation, video-generation, audio-generation,\n    3d-generation) returns a `status` of `\"processing\"` along with a numeric `id`.\n\n    Pass the `id` from the original generation response and the `type` matching the category\n    of the original request (e.g. \"images\" for image-generation).\n\n    The response will contain:\n    - `status`: \"success\", \"processing\", or \"error\"\n    - `output`: array of URLs when status is \"success\"",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "The numeric id returned by a generation tool when status was \"processing\".",
            "type": "integer"
          },
          "type": {
            "description": "The generation category matching the original request: \"images\", \"videos\", \"audios\", or \"3ds\".",
            "enum": [
              "images",
              "videos",
              "audios",
              "3ds"
            ],
            "type": "string"
          }
        },
        "required": [
          "id",
          "type"
        ],
        "type": "object"
      },
      "name": "fetch-generation",
      "outputSchema": null
    },
    {
      "description": "    Generate images using the ModelsLab V8 API.\n    Supports any image endpoint (text-to-image, image-to-image, inpaint, outpaint, fashion, virtual-try-on, etc.).\n    Pass the `endpoint` slug (e.g. \"text-to-image\") and all required parameters for that endpoint.\n    Returns a request ID that can be used with the fetch-generation tool to retrieve results.\n    Use the list-models tool to find available model IDs.",
      "inputSchema": {
        "properties": {
          "endpoint": {
            "description": "The image operation slug.",
            "enum": [
              "flux-headshot"
            ],
            "type": "string"
          },
          "model_id": {
            "description": "The model ID to use for image generation.",
            "type": "string"
          },
          "params": {
            "description": "Additional parameters for the endpoint (e.g. prompt, negative_prompt, width, height, init_image, mask_image, webhook, track_id).",
            "type": "object"
          }
        },
        "required": [
          "model_id",
          "endpoint"
        ],
        "type": "object"
      },
      "name": "image-generation",
      "outputSchema": null
    },
    {
      "description": "    List available AI models on the ModelsLab platform.\n    Filter by category (imagen, video, audio, llm, 3d), provider, tags, and more.\n    Returns model IDs that can be used with generation tools.",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Filter by model category (e.g., \"stable_diffusion\", \"stable_diffusion_xl\", \"flux\", \"llm\", \"video\", \"voice_cloning\").",
            "type": "string"
          },
          "feature": {
            "description": "Filter by product feature: \"imagen\" (images), \"videofusion\" (videos), \"audiogen\" (audio/voice), \"llmaster\" (LLMs), \"threedverse\" (3D).",
            "type": "string"
          },
          "limit": {
            "default": 20,
            "description": "Maximum number of models to return (1-100).",
            "type": "integer"
          },
          "nsfw": {
            "description": "Set to false to exclude NSFW models, true to include them. Defaults to user preference.",
            "type": "boolean"
          },
          "provider": {
            "description": "Filter by model provider (e.g., \"modelslab\", \"civitai\").",
            "enum": [
              "alibaba_cloud",
              "bfl",
              "byteplus",
              "elevenlabs",
              "google",
              "groq",
              "higgsfield",
              "inworld",
              "klingai",
              "ltx",
              "minimax",
              "modelslab",
              "mulerouter",
              "open_router",
              "openai",
              "recraft",
              "runway_ml",
              "skyreels",
              "sonauto",
              "sync",
              "tencent",
              "together_ai",
              "vidu",
              "xai",
              "zoho"
            ],
            "type": "string"
          },
          "search": {
            "description": "Search models by name, ID, description, or tags.",
            "type": "string"
          },
          "sort": {
            "default": "recommended",
            "description": "Sort order: \"recommended\" (default), \"latest\", \"most-used\".",
            "type": "string"
          },
          "subcategory": {
            "description": "Filter by model subcategory (e.g., \"lora\", \"controlnet\", \"embeddings\", \"checkpoint\").",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list-models",
      "outputSchema": null
    },
    {
      "description": "    List all available model providers on the ModelsLab platform.\n    Returns provider names with model counts for each.\n    Use provider names to filter models in the list-models tool.",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Filter providers by model category (e.g., \"stable_diffusion\", \"flux\", \"llm\", \"video\").",
            "type": "string"
          },
          "feature": {
            "description": "Filter providers by product feature: \"imagen\" (images), \"videofusion\" (videos), \"audiogen\" (audio/voice), \"llmaster\" (LLMs), \"threedverse\" (3D).",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list-providers",
      "outputSchema": null
    },
    {
      "description": "    Generate videos using the ModelsLab V8 API.\n    Supports any video endpoint (text-to-video, image-to-video, video-to-video, lip-sync, motion-control, etc.).\n    Pass the `endpoint` slug (e.g. \"text-to-video\") and all required parameters for that endpoint.\n    Returns a request ID that can be used with the fetch-generation tool to retrieve results.\n    Use the list-models tool to find available model IDs.",
      "inputSchema": {
        "properties": {
          "endpoint": {
            "description": "The video operation slug.",
            "enum": [],
            "type": "string"
          },
          "model_id": {
            "description": "The model ID to use for video generation.",
            "type": "string"
          },
          "params": {
            "description": "Additional parameters for the endpoint (e.g. prompt, init_image, init_video, init_audio, duration, aspect_ratio, webhook, track_id).",
            "type": "object"
          }
        },
        "required": [
          "model_id",
          "endpoint"
        ],
        "type": "object"
      },
      "name": "video-generation",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:67a8c651f8973497f824ab68ea8fd2199abe84d62314ebb54291bf9e3e501585 | sha256sum