Replicate MCP server

This Python-based MCP server allows you to interface with Replicate's API through a standardized interface, providing easy access to various AI models for image generation and other tasks.

Installation

Follow these simple steps to get the MCP server up and running:

1. Install the required dependencies:

pip install -r requirements.txt

2. Create a .env file in the root directory and add your Replicate API token:

REPLICATE_API_TOKEN=your_token_here

Starting the Server

Once you've completed the installation, you can launch the server using the FastMCP command:

fastmcp dev server.py

Using the Server

Supported Features

The MCP server currently supports image generation models with the following capabilities:

• Model schema inspection - Examine available parameters and settings
• Image generation with customizable parameters
• Output resizing and optimization for generated images

Making API Requests

After starting the server, you can interact with it by sending HTTP requests to the appropriate endpoints. The server follows the Model Context Protocol standard for request and response formatting.

Example Usage

While specific endpoint documentation may vary based on your server implementation, typical usage patterns include:

1. Inspecting available models
2. Selecting a model and configuring generation parameters
3. Sending generation requests
4. Processing the returned image data

Coming Soon

The server is under active development with plans to add support for:

• Text generation (completion models, chat models, streaming)
• Video generation with optimization and progress tracking
• Model version management and improved error handling

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "replicate" '{"command":"fastmcp","args":["dev","server.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "replicate": {
            "command": "fastmcp",
            "args": [
                "dev",
                "server.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "replicate": {
            "command": "fastmcp",
            "args": [
                "dev",
                "server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect