Replicate Automation

AutomationAuto-detects your installed agents and installs the skill to each one.

What This Skill Does

• This skill automates workflows for Replicate, an AI model platform.
• It allows users to run predictions on public models, upload input files, inspect model schemas, and track prediction history.
• It's designed for developers and researchers who want to integrate AI models into their applications.

When to Use

• Generate images from text prompts.
• Run language models for text completion.
• Process audio and video files.
• Integrate AI models into web applications.
• Automate AI-powered content creation.
• Experiment with different AI models.

Key Features

• Supports running predictions on any public Replicate model.
• Allows uploading input files for model processing.
• Provides tools to inspect model schemas and documentation.
• Enables listing model versions.
• Tracks prediction history.
• Offers synchronous and asynchronous prediction execution.

Replicate Automation

Automate your Replicate AI model workflows -- run predictions on any public model (image generation, LLMs, audio, video), upload input files, inspect model schemas and documentation, list model versions, and track prediction history.

Toolkit docs: composio.dev/toolkits/replicate

Setup

Add the Composio MCP server to your client: https://rube.app/mcp Connect your Replicate account when prompted (API token authentication) Start using the workflows below

Core Workflows

1. Get Model Details and Schema

Use REPLICATE_MODELS_GET to inspect a model's input/output schema before running predictions.

Tool: REPLICATE_MODELS_GET Inputs:

• model_owner: string (required) -- e.g., "meta", "black-forest-labs", "stability-ai"
• model_name: string (required) -- e.g., "meta-llama-3-8b-instruct", "flux-1.1-pro"

Important: Each model has unique input keys and types. Always check the openapi_schema from this response before constructing prediction inputs.

2. Run a Prediction

Use REPLICATE_MODELS_PREDICTIONS_CREATE to run inference on any model with optional synchronous waiting and webhooks.

Tool: REPLICATE_MODELS_PREDICTIONS_CREATE Inputs:

• model_owner: string (required) -- e.g., "meta", "black-forest-labs"
• model_name: string (required) -- e.g., "flux-1.1-pro", "sdxl"
• input: object (required) -- model-specific inputs, e.g., { "prompt": "A sunset over mountains" }
• wait_for: integer (1-60 seconds, optional) -- synchronous wait for completion
• cancel_after: string (optional) -- max execution time, e.g., "300s", "5m"
• webhook: string (optional) -- HTTPS URL for async completion notifications
• webhook_events_filter: array (optional) -- ["start", "output", "logs", "completed"]

Sync vs Async: Use wait_for (1-60s) for fast models. For long-running jobs, omit it and use webhooks or poll via REPLICATE_PREDICTIONS_LIST.

3. Upload Files for Model Input

Use REPLICATE_CREATE_FILE to upload images, documents, or other binary inputs that models need.

Tool: REPLICATE_CREATE_FILE Inputs:

• content: string (required) -- base64-encoded file content
• filename: string (required) -- e.g., "input.png", "audio.wav" (max 255 bytes UTF-8)
• content_type: string (default "application/octet-stream") -- MIME type
• metadata: object (optional) -- custom JSON metadata

4. Read Model Documentation

Use REPLICATE_MODELS_README_GET to access a model's README in Markdown format for detailed usage instructions.

Tool: REPLICATE_MODELS_README_GET Inputs:

• model_owner: string (required)
• model_name: string (required)

5. List Model Versions

Use REPLICATE_MODELS_VERSIONS_LIST to see all available versions of a model, sorted newest first.

Tool: REPLICATE_MODELS_VERSIONS_LIST Inputs:

• model_owner: string (required)
• model_name: string (required)

6. Track Prediction History and Files

Use REPLICATE_PREDICTIONS_LIST to retrieve prediction history, and REPLICATE_FILES_GET/REPLICATE_FILES_LIST to manage uploaded files.

Tool: REPLICATE_PREDICTIONS_LIST

• Lists all predictions for the authenticated user with pagination

Tool: REPLICATE_FILES_LIST

• Lists uploaded files, most recent first

Tool: REPLICATE_FILES_GET

• Get details of a specific file by ID

Known Pitfalls

Quick Reference