Sponsored by Deepsite.site

Image MCP Servers

Created By
fabelis8 months ago
Content

Image MCP Servers

Fabelis Building Fabelis Compare Fabelis Castle

This project implements an SSE MCP server that exposes tools for interacting with HuggingFace and Replicate APIs, focusing on image generation and model management. It's built using the MCP Core framework and provides a standardized interface for AI model interactions. Below is a guide to host it yourself!

Features

HuggingFace Logo Replicate Logo

HuggingFace Integration

ToolDescription
Get Model InfoRetrieve detailed information about models on HuggingFace
Get Model Sample ImagesExtract sample images from model READMEs
Get ReadmeFetch the README content for a model
Search ModelsSearch for models on HuggingFace with filtering options
WhoAmIRetrieve information about the current HuggingFace API token

Replicate Integration

ToolDescription
Generate ImageCreate images using Replicate's text-to-image models
Get Model InfoRetrieve detailed information about models on Replicate
Get PredictionCheck the status and retrieve outputs of a prediction
List ModelsList available models on Replicate with optional filtering
WhoAmIRetrieve information about the current Replicate API token

Getting Started

Prerequisites

  • Rust (2024 edition)
  • Docker (optional, for containerized deployment)

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/image-mcp-servers.git
    cd image-mcp-servers
    
  2. Create a .env file based on the .env.example:

    cp .env.example .env
    
  3. Add your API tokens to the .env file:

    HF_API_TOKEN="your_huggingface_token"
    REPLICATE_API_TOKEN="your_replicate_token"
    
  4. Build the project:

    cargo build
    

Running the Server

cargo run

The server will start on the port specified in the SERVER_PORT environment variable (default: 3000).

Using Docker

The project includes Docker support for easy deployment:

# Start the service
just docker-up service

# Stop the service
just docker-down service

Configuration

The server can be configured using environment variables:

  • SERVER_NAME: Name of the server (default: "image-mcp-servers")
  • SERVER_VERSION: Version of the server (default: "0.1.0")
  • SERVER_PORT: Port to run the server on (default: 3000)
  • HF_API_TOKEN: HuggingFace API token
  • REPLICATE_API_TOKEN: Replicate API token

Features

The project supports two main feature sets that can be enabled or disabled:

  • huggingface: Enables HuggingFace API integration
  • replicate: Enables Replicate API integration

By default, no features are enabled. You can build with specific features:

# Build with only HuggingFace
cargo build --no-default-features --features huggingface

# Build with only Replicate
cargo build --no-default-features --features replicate

License

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

Acknowledgements

  • MCP Core - The framework used for building this server
  • HuggingFace - For their image generation models
  • Replicate - For their image generation API
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Serper MCP ServerA Serper MCP Server
DeepChatYour AI Partner on Desktop
ChatWiseThe second fastest AI chatbot™
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Amap Maps高德地图官方 MCP Server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Tavily Mcp
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Playwright McpPlaywright MCP server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
CursorThe AI Code Editor
WindsurfThe new purpose-built IDE to harness magic
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.