MCP Tools & Resources

This reference is auto-generated from the running MCP server.

Workflow

AI agents should follow this workflow to run pipelines:

1. list_pipelines — discover available pipelines
2. get_pipeline_schema — get the input schema for the chosen pipeline
3. request_upload — upload any required files (images, videos, audio)
4. run_pipeline — run the pipeline with the required input
5. get_pipeline_run_status — check the result (or wait for real-time notifications)

Tip

After calling run_pipeline, the server automatically subscribes to status updates. Your assistant will receive notifications/pipeline/status as the pipeline progresses through pending → running → completed (or failed).

---

Tools

list_pipelines

List all available AI video/image pipelines. Returns name, slug, description, category, credit cost, and required providers for each active pipeline.

Parameters: None

---

get_pipeline_schema

Get the input schema for a specific pipeline. Returns the JSON Schema describing required and optional input fields. Use this before running a pipeline to understand what inputs are needed.

Parameters:

Name	Type	Required	Description
pipeline_slug	string	Yes	The slug identifier of the pipeline (e.g., ‘image-generator’, ‘video-generator’)

---

run_pipeline

Run an AI pipeline by slug with the given input. Use list_pipelines to discover available pipelines and get_pipeline_schema to see required inputs. Returns a run ID for tracking status.

Parameters:

Name	Type	Required	Description
input	object	Yes	Pipeline input fields as a JSON object. Use get_pipeline_schema to see required fields for each pipeline.
pipeline_slug	string	Yes	The slug identifier of the pipeline to run (e.g., ‘image-generator’, ‘video-generator’)

---

get_pipeline_run_status

Check the status of a pipeline run. Returns status (pending/running/completed/failed), output data, error messages, timestamps, and generated asset URLs.

Parameters:

Name	Type	Required	Description
run_id	string	Yes	The pipeline run ID returned by run_pipeline

---

request_upload

Request a presigned S3 upload URL for a file. Use this for pipeline inputs that require file URLs (e.g., images, videos, audio).

Two-step upload flow:

1. Call this tool with filename and content_type to get a presigned upload URL and final asset URL
2. PUT the file contents to the upload_url (presigned, expires in 5 minutes)
3. Use the asset_url as the input value when running a pipeline

Supported content types: image/* (max 10MB), video/* (max 50MB), audio/* (max 20MB)

Parameters:

Name	Type	Required	Description
content_type	string	Yes	MIME type of the file (e.g., ‘image/jpeg’, ‘image/png’, ‘video/mp4’, ‘audio/mpeg’)
filename	string	Yes	Name of the file to upload (e.g., ‘photo.jpg’, ‘video.mp4’)

---

---

Resources

billing://balance

Credit Balance

Your current credit balance, including available and reserved credits.

MIME type: application/json

---

billing://history

Credit History

Your credit transaction history showing purchases, usage, and refunds.

MIME type: application/json

---

assets://list

List Assets

List your generated assets (images, videos, audio). All assets from pipeline runs.

MIME type: application/json

---

assets://get/{asset_id}

Get Asset

Get details of a specific asset by ID, including metadata and download URL.

MIME type: application/json

---

assets://list/{type}

List Assets by Type

List your generated assets filtered by type (image, video, audio).

MIME type: application/json

---

---

Real-Time Notifications

When you run a pipeline, the MCP server automatically subscribes to status updates. Notifications use method notifications/pipeline/status:

{
  "method": "notifications/pipeline/status",
  "params": {
    "run_id": "uuid",
    "status": "completed",
    "pipeline_name": "Pipeline Name",
    "pipeline_slug": "pipeline-slug",
    "assets": [
      {
        "id": "uuid",
        "url": "https://s3.pipe2.ai/assets/...",
        "type": "image"
      }
    ]
  }
}

Status values: pending, running, completed, failed, cancelled