MCP For Claude Marketplace
Replicate

Replicate MCP Connector for Claude

A+

Run ML models via Replicate — generate images, text, audio and video from community models, track predictions and explore collections from any AI agent.

12 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Replicate account to any AI agent and run thousands of open-source ML models through natural conversation.

What you can do

  • Model Discovery — Browse, search and inspect thousands of ML models with their descriptions, run counts and hardware requirements
  • Predictions — Run models by creating predictions and tracking their status (starting, processing, succeeded, failed)
  • Collections — Explore curated collections of models by category (text-to-image, LLMs, audio, video)
  • Hardware Options — View available GPU types and pricing for model inference
  • Account Info — Check your account details and usage

How it works

  1. Subscribe to this server
  2. Enter your Replicate API Token
  3. Start running ML models from Claude, Cursor, or any MCP-compatible client

No more navigating the Replicate website to find models or check prediction status. Your AI acts as a dedicated ML operations assistant.

Who is this for?

  • Developers — quickly run image generation, text models and other ML predictions via conversation
  • ML Engineers — discover models, compare hardware requirements and track prediction history
  • Researchers — explore model collections, inspect version schemas and test models before deployment
machine-learningmodel-inferencegenerative-aiapi-integrationcloud-computing

12 tools expose this connector's capabilities to your AI agent.

cancel_prediction

Provide the prediction ID. The prediction status will change to "canceled". Cancel a running prediction

create_prediction

Requires the model slug in "owner/name" format and an input object matching the model's schema. Optionally specify a version ID and webhook URL. Returns the prediction object with its ID, status (starting, processing, succeeded, failed, canceled) and output. Use get_prediction to check status and retrieve results. Run a model prediction on Replicate

get_account

Returns account type, username and usage info. Use this to verify your API token is working correctly. Get the authenticated Replicate account info

get_collection

Provide the collection slug (e.g. "text-to-image", "large-language-models"). Get details for a specific model collection

get_model

Provide the model slug in "owner/name" format (e.g. "stability-ai/sdxl" or "meta/meta-llama-3-70b-instruct"). Get details for a specific Replicate model

get_model_versions

Each version includes its ID (64-char hash), creation date, input/output schema and cog version. Use this to find the correct version ID when creating predictions for models that require a specific version. Get all versions of a Replicate model

get_prediction

Returns the prediction ID, status (starting, processing, succeeded, failed, canceled), input, output URLs, creation time and logs. Use the prediction ID returned from create_prediction. Get the status and result of a prediction

list_collections

Collections group related models by category (e.g. "text-to-image", "large-language-models", "audio-to-audio", "image-to-video"). Each collection includes its slug, name, description and featured models. List model collections on Replicate

list_hardware

Each hardware option includes its SKU name, pricing and specifications. Useful for choosing the right GPU for your prediction workload. List available GPU hardware on Replicate

list_models

Each model includes its name, owner, description, run count, hardware requirements and cover image URL. Use this to discover available models for running predictions. List available ML models on Replicate

list_predictions

Each prediction includes its ID, model, status, creation time and output URLs. Useful for tracking prediction history and monitoring model usage. List recent predictions on Replicate

search_models

Returns models with their name, owner, description, run count and hardware. Useful for finding specific types of models (e.g. "text-to-image", "llm", "music-generation"). Search for models on Replicate by query

See how to talk to your AI agent using Replicate.

List all text-to-image collections on Replicate.

Found the 'text-to-image' collection with featured models including stability-ai/sdxl, black-forest-labs/flux-schnell, and ideogram-ai/ideogram-v2. The collection has 50+ models total.

Search for LLM models on Replicate.

Found popular LLM models: meta/meta-llama-3-70b-instruct (2M+ runs), mistralai/mistral-7b-instruct-v0.3 (1.5M+ runs), google/gemma-2-27b-it (800K+ runs). Each model shows hardware requirements and example inputs.

Create a prediction using stability-ai/sdxl with prompt 'a sunset over mountains, photorealistic'.

Created prediction pred_abc123. Status: starting. Check back with `get_prediction` to retrieve the generated image URL once it completes (usually 10-30 seconds).

Log in to the [**Replicate API Tokens page**](https://replicate.com/account/api-tokens) and click **Create API Token**. Copy the token immediately — it starts with `r8_` and won't be shown again.

Related Connectors

OF

OfficeRnD Flex MCP

10 tools Official

Manage flexible workspaces via OfficeRnD — track members, bookings, and billing directly from your AI agent.

A+ View details →
AS

Amazon SQS Queue MCP

3 tools Official

This MCP does exactly one thing: it pulls and acknowledges messages from a single Amazon SQS Queue. That's its only function, and nothing else. Incredible for building secure AI workers.

F View details →
RA

Railway MCP

11 tools Official

Manage cloud deployments via Railway — list projects, inspect services, track deployments and manage variables and volumes from any AI agent.

A+ View details →
TR

Truepill MCP

7 tools Official

Manage pharmacy operations and patient records via Truepill — create patients, find records, and track prescriptions directly from any AI agent.

A+ View details →