Replicate

What is mcp-replicate?

mcp-replicate is a Model Context Protocol (MCP) server specifically designed to integrate with Replicate's API. It enables users to search, run, and manage machine learning models available on Replicate directly through MCP-compatible clients like Claude Desktop, Cursor, Cline, or Continue. This project simplifies the interaction with complex ML models by providing a structured, tool-based interface.

How to use mcp-replicate?

To use mcp-replicate, you can follow these steps:

1. Installation: Install the server globally via npm: npm install -g mcp-replicate. Alternative installation methods include installing from source or running with npx.
2. Replicate API Token: Obtain your Replicate API token from the Replicate API tokens page.
3. Configuration: Configure your MCP client (e.g., Claude Desktop) by adding the mcp-replicate server and your Replicate API token to its configuration file. For Claude Desktop, this involves editing the mcpServers section in the developer settings.
4. Start Client: Launch your MCP client. You should see an indicator (e.g., a hammer icon in Claude Desktop) confirming the tools are available.

Key Features of mcp-replicate

mcp-replicate offers a comprehensive set of features for interacting with Replicate models:

• Models: Search models using semantic search, browse models and collections, and get detailed model information and versions.
• Predictions: Create predictions with various input types, track their status, cancel running predictions, and list recent predictions.
• Image Handling: View generated images directly in your browser and manage an image cache for improved performance.
• Tooling: Provides a rich set of tools categorized into Model Tools (e.g., search_models, list_models), Prediction Tools (e.g., create_prediction, get_prediction), and Image Tools (e.g., view_image, clear_image_cache).

Use Cases of mcp-replicate

mcp-replicate is ideal for:

• Developers and Researchers: Easily integrate Replicate's machine learning capabilities into their workflows and applications.
• AI Enthusiasts: Experiment with various ML models without deep technical knowledge of the underlying APIs.
• Content Creators: Generate images and other media using AI models and manage them efficiently.
• Anyone needing quick access to ML models: Utilize a simplified interface to run and manage predictions for various tasks.

FAQ from mcp-replicate

Q: Server is running but tools aren't showing up. What should I do? A: Check that your MCP client (e.g., Claude Desktop) is properly configured with the MCP server settings. Ensure your Replicate API token is set correctly. Try restarting both the server and your client, and review server logs for error messages.

Q: Tools are visible but not working. How can I troubleshoot this? A: Verify that your Replicate API token is valid and check your internet connection. Look for any error messages in the server output for more specific guidance.

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

2. Get your Replicate API token:

   • Go to Replicate API tokens page
   • Create a new token if you don't have one
   • Copy the token for the next step

3. 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"
      }
    }
  }
}

4. 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

2. Start development server (with auto-reload):

npm run dev

3. Check code style:

npm run lint

4. Format code:

npm run format

Requirements

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

License

MIT