MCP ExplorerExplorer

Replicate

@deepfateson 2 months ago
69 MIT
FreeCommunity
AI Systems
#Replicate#API
Search, run and manage machine learning models on Replicate through a simple tool-based interface. Browse models, create predictions, track their status, and handle generated images.

Overview

What is Replicate

MCP Server for Replicate is an implementation that facilitates executing machine learning models via a straightforward tool-based interface. It leverages the Model Context Protocol to connect to Replicate, allowing users to interact with various AI models seamlessly.

Use cases

This tool is beneficial for developers and data scientists who require an efficient means to explore and utilize AI models for tasks like text generation, image creation, and semantic searches. It simplifies the prediction process, enabling the management of model interactions and predictions through an accessible interface.

How to use

To use the MCP Server for Replicate, install it via npm, obtain a Replicate API token, and configure it within Claude Desktop. After setting up, users can access a range of tools to manage models and predictions, with a user-friendly interface for model selection and interaction.

Key features

Key features include the ability to search available models semantically, create and manage predictions, track prediction statuses, cancel running predictions, and handle image outputs effectively. Additionally, users can browse model collections and access model details.

Where to use

This tool is intended for use within Claude Desktop but can also function with other MCP clients. It provides a versatile environment for users looking to harness the capabilities of Replicate’s machine learning models in various applications, from development to research.

Content

Replicate MCP Server

A Model Context Protocol server implementation for Replicate. Run Replicate models through a simple tool-based interface.

Quickstart

  1. Install the server:
npm install -g mcp-replicate
  1. Get your Replicate API token:

  2. Configure Claude Desktop:

    • Open Claude Desktop Settings (,)
    • Select the “Developer” section in the sidebar
    • Click “Edit Config” to open the configuration file
    • Add the following configuration, replacing your_token_here with your actual Replicate API token:
{
  "mcpServers": {
    "replicate": {
      "command": "mcp-replicate",
      "env": {
        "REPLICATE_API_TOKEN": "your_token_here"
      }
    }
  }
}
  1. Start Claude Desktop. You should see a 🔨 hammer icon in the bottom right corner of new chat windows, indicating the tools are available.

(You can also use any other MCP client, such as Cursor, Cline, or Continue.)

Alternative Installation Methods

Install from source

git clone https://github.com/deepfates/mcp-replicate
cd mcp-replicate
npm install
npm run build
npm start

Run with npx

npx mcp-replicate

Features

Models

  • Search models using semantic search
  • Browse models and collections
  • Get detailed model information and versions

Predictions

  • Create predictions with text or structured input
  • Track prediction status
  • Cancel running predictions
  • List your recent predictions

Image Handling

  • View generated images in your browser
  • Manage image cache for better performance

Configuration

The server needs a Replicate API token to work. You can get one at Replicate.

There are two ways to provide the token:

1. In Claude Desktop Config (Recommended)

Add it to your Claude Desktop configuration as shown in the Quickstart section:

{
  "mcpServers": {
    "replicate": {
      "command": "mcp-replicate",
      "env": {
        "REPLICATE_API_TOKEN": "your_token_here"
      }
    }
  }
}

2. As Environment Variable

Alternatively, you can set it as an environment variable if you’re using another MCP client:

export REPLICATE_API_TOKEN=your_token_here

Available Tools

Model Tools

  • search_models: Find models using semantic search
  • list_models: Browse available models
  • get_model: Get details about a specific model
  • list_collections: Browse model collections
  • get_collection: Get details about a specific collection

Prediction Tools

  • create_prediction: Run a model with your inputs
  • create_and_poll_prediction: Run a model with your inputs and wait until it’s completed
  • get_prediction: Check a prediction’s status
  • cancel_prediction: Stop a running prediction
  • list_predictions: See your recent predictions

Image Tools

  • view_image: Open an image in your browser
  • clear_image_cache: Clean up cached images
  • get_image_cache_stats: Check cache usage

Troubleshooting

Server is running but tools aren’t showing up

  1. Check that Claude Desktop is properly configured with the MCP server settings
  2. Ensure your Replicate API token is set correctly
  3. Try restarting both the server and Claude Desktop
  4. Check the server logs for any error messages

Tools are visible but not working

  1. Verify your Replicate API token is valid
  2. Check your internet connection
  3. Look for any error messages in the server output

Development

  1. Install dependencies:
npm install
  1. Start development server (with auto-reload):
npm run dev
  1. Check code style:
npm run lint
  1. Format code:
npm run format

Requirements

  • Node.js >= 18.0.0
  • TypeScript >= 5.0.0
  • Claude Desktop for using the tools

License

MIT

Tools

search_models
Search for models using semantic search
list_models
List available models with optional filtering
list_collections
List available model collections
get_collection
Get details of a specific collection
create_prediction
Create a new prediction using either a model version (for community models) or model name (for official models)
cancel_prediction
Cancel a running prediction
get_prediction
Get details about a specific prediction
list_predictions
List recent predictions
get_model
Get details of a specific model including available versions
view_image
Display an image in the system's default web browser
clear_image_cache
Clear the image viewer cache
get_image_cache_stats
Get statistics about the image cache

Comments

Recommend MCP Servers

View All MCP Servers