Replicate

by gerred

10 stars

16.6k downloads

Not rated

GitHub

About

Integrates with Replicate API to provide seamless access to diverse machine learning models for inference and result retrieval across various domains.

Details

Author: gerred
Repository: gerred/mcp-server-replicate
GitHub stars: 10
Downloads: 16,561
Categories: Cloud Service, AI, API, Design, Developer Tools, Search, Infrastructure, Frontend, Other

- 🖼️ Resource-based image generation and management
- 🔄 Real-time updates through subscriptions
- 📝 Template-driven parameter configuration
- 🔍 Comprehensive model discovery and selection
- 🪝 Webhook integration for external notifications
- 🎨 Quality and style presets for optimal results
- 📊 Progress tracking and status monitoring
- 🔒 Secure API key management

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Replicate

Command (node, npx, python, etc.) uv
Arguments
- Argument 1 tool
- Argument 2 run
- Argument 3 mcp-server-replicate
Environment
- REPLICATE_API_TOKEN APITOKEN
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

From the repository

Install via Smithery (npx -y @smithery/cli install @gerred/mcp-server-replicate --client claude) or manually with uv pip install mcp-server-replicate. Configure the server in claude_desktop_config.json using the uv command and set the REPLICATE_API_TOKEN environment variable. Once connected, use natural language prompts in Claude Desktop to generate images, browse generations, search, or check status.

`Generate Images`

Generate images with natural language descriptions. Example usage: 'Create a photorealistic mountain landscape at sunset with snow-capped peaks'.

`Browse Generations`

View the recent image generations created by the user. Example usage: 'Show me my recent image generations'.

`Search Generations`

Search through previous image generations based on specific criteria. Example usage: 'Find my landscape generations'.

`Check Generation Status`

Check the status of the most recent image generation. Example usage: 'What's the status of my last generation?'.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "replicate": {
            "cwd": "$$PATH_TO_REPO",
            "env": {
                "REPLICATE_API_TOKEN": "APITOKEN"
            },
            "args": [
                "tool",
                "run",
                "mcp-server-replicate"
            ],
            "command": "uv"
        }
    }
}

Linux

{
    "cwd": "$$PATH_TO_REPO",
    "env": {
        "REPLICATE_API_TOKEN": "APITOKEN"
    },
    "args": [
        "tool",
        "run",
        "mcp-server-replicate"
    ],
    "command": "uv"
}

Macos

{
    "cwd": "$$PATH_TO_REPO",
    "env": {
        "REPLICATE_API_TOKEN": "APITOKEN"
    },
    "args": [
        "tool",
        "run",
        "mcp-server-replicate"
    ],
    "command": "uv"
}

Windows

{
    "cwd": "$$PATH_TO_REPO",
    "env": {
        "REPLICATE_API_TOKEN": "APITOKEN"
    },
    "args": [
        "tool",
        "run",
        "mcp-server-replicate"
    ],
    "command": "uv"
}

A FastMCP server implementation for the Replicate API, providing resource-based access to AI model inference with a focus on image generation.

The server provides several specialized prompts for different tasks:

Our most thoroughly tested and robust prompt. Optimized for generating high-quality images from text descriptions with:

- Detailed style control
- Quality presets (draft, balanced, quality, extreme)
- Size and aspect ratio customization
- Progress tracking and real-time updates

Create a photorealistic mountain landscape at sunset with snow-capped peaks, quality level: quality, style: photorealistic

- Image to Image: Transform existing images (coming soon)
- Model Selection: Get help choosing the right model for your task
- Parameter Help: Understand and configure model parameters

- Python 3.11 or higher
- A Replicate API key (get one athttps://replicate.com/account)
- UVfor dependency management

To install MCP Server Replicate for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gerred/mcp-server-replicate --client claude

You can install the package directly from PyPI:

# Using UV (recommended) uv pip install mcp-server-replicate # Using UVX for isolated environments uvx install mcp-server-replicate # Using pip pip install mcp-server-replicate

- Make sure you have the latest version of Claude Desktop installed
- Open your Claude Desktop configuration:

# macOS code ~/Library/Application\ Support/Claude/claude_desktop_config.json # Windows code %APPDATA%\Claude\claude_desktop_config.json

- Add the server configuration using one of these options:

{ "globalShortcut": "Shift+Alt+A", "mcpServers": { "replicate": { "command": "uv", "args": ["tool", "run", "mcp-server-replicate"], "env": { "REPLICATE_API_TOKEN": "APITOKEN" }, "cwd": "$PATH_TO_REPO" } } }

# Option 1: Set in your environment export REPLICATE_API_TOKEN=your_api_key_here # Option 2: Create a .env file in your home directory echo "REPLICATE_API_TOKEN=your_api_key_here" > ~/.env

You should now see the 🔨 icon in Claude Desktop, indicating that the MCP server is available.

Once connected to Claude Desktop, you can:

Create a photorealistic mountain landscape at sunset with snow-capped peaks

What's the status of my last generation?

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

- Make sure the path inclaude_desktop_config.jsonis absolute
- Ensure UV is installed and in your PATH
- Check that your Replicate API key is set

For more detailed troubleshooting, see ourDebugging Guide.

- Implementation Plan
- Contributing Guide
- API Reference
- Resource System
- Template System

git clone https://github.com/gerred/mcp-server-replicate.git cd mcp-server-replicate

uv pip install --system ".[dev]"

We welcome contributions! Please see ourContributing Guidefor details.

This project is licensed under the MIT License - see the LICENSEfile for details.

Access DeepSeek's advanced language models via the DeepSeek API.

Advanced text-to-image generation model with superior quality and text rendering via the fal.ai API.

Advanced text-to-image generation model using the fal.ai API. Requires a FAL_KEY environment variable.

Integrate with the Grok AI API to access its powerful language models.

A unified interface to various LLM providers like OpenAI, Anthropic, and Google using Pydantic AI.

A server for interacting with the OpenAI API. Requires an OpenAI API key.

Image analysis using OpenRouter's vision models.

Interact with the Novita AI API for image generation and other AI tasks.

A server for interacting with the OpenAI API. Requires an API key.

A bridge to OpenAI's Chat Completion and Assistants APIs.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Generate Images

Browse Generations

Search Generations

Check Generation Status

Claude Desktop / Cursor

Linux

Macos

Windows

Install

More like this

Aws Kb Retrieval Server

GitLab

Context 7

1Panel

🔎 GPT Researcher

Serena

`Generate Images`

`Browse Generations`

`Search Generations`

`Check Generation Status`