The Replicate MCP Server allows you to interact with Replicate models through a tool-based interface, providing the following capabilities:
Search and Browse Models: Search for models using semantic search, list available models, or browse model collections
Get Model Details: Retrieve detailed information about specific models and collections
Create and Manage Predictions: Generate predictions with your chosen models, track prediction status, cancel running predictions, and view recent predictions
Image Handling: View generated images in your browser, manage the image cache, and check cache usage statistics
Integration: Configurable with a Replicate API token for seamless integration with MCP clients like Claude Desktop, Cursor, Cline, or Continue
Allows running Replicate models through a Model Context Protocol (MCP) server implementation. Provides tools for searching models, creating predictions, tracking prediction status, and handling generated images.
A Model Context Protocol server implementation for Replicate. Run Replicate models through a simple tool-based interface.
Install the server:
Get your Replicate API token:
Create a new token if you don't have one
Copy the token for the next step
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:
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.)
Search models using semantic search
Browse models and collections
Get detailed model information and versions
Create predictions with text or structured input
Track prediction status
Cancel running predictions
List your recent predictions
View generated images in your browser
Manage image cache for better performance
The server needs a Replicate API token to work. You can get one at Replicate.
There are two ways to provide the token:
Add it to your Claude Desktop configuration as shown in the Quickstart section:
Alternatively, you can set it as an environment variable if you're using another MCP client:
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
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
view_image: Open an image in your browser
clear_image_cache: Clean up cached images
get_image_cache_stats: Check cache usage
Check that Claude Desktop is properly configured with the MCP server settings
Ensure your Replicate API token is set correctly
Try restarting both the server and Claude Desktop
Check the server logs for any error messages
Verify your Replicate API token is valid
Check your internet connection
Look for any error messages in the server output
Install dependencies:
Start development server (with auto-reload):
Check code style:
Format code:
Node.js >= 18.0.0
TypeScript >= 5.0.0
Claude Desktop for using the tools
MIT
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables users to access and manage Replicate's AI models and predictions via the Model Context Protocol, offering tools for creating, canceling, and retrieving model predictions and parameters.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/deepfates/mcp-replicate'
If you have feedback or need assistance with the MCP directory API, please join our Discord server