MCP Server TEST1

This project implements an MCP server that integrates Venice AI's image - generation capabilities, providing an interactive image - generation service with an approval/regeneration workflow and supporting the generation of multi - view 3D views through the Gemini API.

Image and video processing Developer tools #Image Generation #AI Interaction #3D Modeling #Workflow .JavaScript

rating : 2 points

downloads : 29

update time : 2025-04-29

What is MCP?

Model Context Protocol (MCP) is an open protocol for standardizing how applications provide context to large language models (LLMs). It's like the 'USB-C interface' for AI applications, enabling LLMs to connect to various data sources and tools.

How to use the Venice AI MCP Server?

Users only need to provide text prompts, and the server will generate images and optimize them through a click - based approval process.

Applicable scenarios

Suitable for scenarios that require high - quality image generation and support multi - view consistency, such as product design, art creation, and 3D modeling.

Main Features

Generate images based on textGenerate high - quality images according to the text prompts provided by users.

Interactive approval processBy clicking the 'Like' or 'Retry' buttons, users can quickly provide feedback and optimize the generated results.

Multi - view consistent generationUse the Gemini API to generate multiple consistent views, ensuring the same style from each angle.

2D image to 3D model conversionConvert 2D images into 3D models, suitable for complex object modeling.

Advantages and Limitations

Advantages

High - quality image generation

Simple and user - friendly interactive interface

Support for multi - view consistency and 3D modeling

Limitations

Dependence on external APIs (such as Venice AI and Gemini)

Requires a stable network environment

How to Use

Installation and Configuration

Download and install the FastMCP library and set the Venice AI API key.

Start the Server

Run the MCP server and connect it to your LLM host.

Send a Generation Request

Send a generation request with a text prompt to the server.

Usage Examples

Generate a future city skylineThe user requests to generate an image of a future city skyline.

Multi - view generationThe user requests to generate images of the same object from different perspectives.

Frequently Asked Questions

How to start using the MCP server?

What if I'm not satisfied with the image?

Does it support custom image sizes?

Related Resources

Official MCP Introduction

Understand the basic concepts of the MCP protocol.

Venice AI API Documentation

Learn in detail about the functions of the Venice AI API.

Gemini API Tutorial

Learn how to use the Gemini API to generate multi - view images.

🚀 Florence AI Image Generator MCP Server

This project implements a Model Context Protocol (MCP) server integrating Venice AI for image generation, combined with approval/regeneration workflows.

🚀 Quick Start

To implement this server, follow these steps:

Install the FastMCP library.
Set up Venice AI API credentials.
Implement the described MCP tools.
Run the server and connect it to the LLM host.

✨ Features

Image Generation and Approval Process

The core functions of this server are as follows:

Generate images based on text prompts using Venice AI.
Overlay clickable up/down vote icons on the images and display them to users.
Allow users to approve an image by clicking the up icon or request regeneration by clicking the down icon.
Regenerate the image with the same parameters if needed.

Technical Implementation

The server implements several MCP tools:

generateImage: Generate an image based on a text prompt.
approveImage: Approve a generated image.
requestRegeneration: Request image regeneration.
showVotes: Display the voting status of the current image.

📚 Documentation

What is MCP?

The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). It acts as the “USB-C port for AI apps,” allowing LLMs to connect to various data sources and tools in a unified way.

For more information, visit the official MCP introduction page.

Project Overview

This MCP server bridges the gap between LLMs (such as Claude) and Venice AI's image generation capabilities. It enables LLMs to generate images based on text prompts and implements an interactive approval feedback loop with up/down vote icons.