About Image MCP Servers
Image MCP Servers is an SSE MCP server exposing tools for the HuggingFace and Replicate APIs. It is for users who need model information, model search, or image generation, and allows either API integration to be enabled at build time.
Key features
- 01Get HuggingFace model details and READMEs
- 02Search HuggingFace models and view sample images
- 03Generate images through Replicate
- 04Inspect Replicate models and prediction results
- 05Enable API integrations through build features
Use cases
- 01Find HuggingFace models and sample images
- 02Read model documentation and details
- 03Generate images with Replicate text-to-image models
- 04Check image prediction status and outputs
MCP support
The SSE MCP server exposes HuggingFace and Replicate tools to MCP clients, including model lookup, search, and image generation.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEImage MCP Servers
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 Integration
| Tool | Description |
|---|---|
| Get Model Info | Retrieve detailed information about models on HuggingFace |
| Get Model Sample Images | Extract sample images from model READMEs |
| Get Readme | Fetch the README content for a model |
| Search Models | Search for models on HuggingFace with filtering options |
| WhoAmI | Retrieve information about the current HuggingFace API token |
Replicate Integration
| Tool | Description |
|---|---|
| Generate Image | Create images using Replicate's text-to-image models |
| Get Model Info | Retrieve detailed information about models on Replicate |
| Get Prediction | Check the status and retrieve outputs of a prediction |
| List Models | List available models on Replicate with optional filtering |
| WhoAmI | Retrieve information about the current Replicate API token |
Getting Started
Prerequisites
- Rust (2024 edition)
- Docker (optional, for containerized deployment)
Installation
-
Clone the repository:
git clone https://github.com/yourusername/image-mcp-servers.git cd image-mcp-servers -
Create a
.envfile based on the.env.example:cp .env.example .env -
Add your API tokens to the
.envfile:HF_API_TOKEN="your_huggingface_token" REPLICATE_API_TOKEN="your_replicate_token" -
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 tokenREPLICATE_API_TOKEN: Replicate API token
Features
The project supports two main feature sets that can be enabled or disabled:
huggingface: Enables HuggingFace API integrationreplicate: 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.