Trendy Post MCP
Enables users to take screenshots, extract text using OCR, and automatically generate trending Xiaohongshu-style social media posts. Combines image processing with AI-powered content generation to create engaging posts with hashtags and titles.
README
Trendy Post MCP 🚀✨
A Model Context Protocol (MCP) service that:
- Takes a screenshot from the user 📸
- Uses OCR to extract text and analyze the image 🔍
- Generates a trending Xiaohongshu-style post based on the content 📱💬
Features ✨
- Image Processing 🖼️: Extract text and analyze images
- Content Generation 📝: Create engaging Xiaohongshu-style posts
- LLM Integration 🧠: Uses AI to generate post styles, hashtags, and titles
- MCP Compatibility 🔌: Works with any MCP client
Setup 🛠️
This MCP uses the trendy_post_mcp conda environment with Python 3.12 and Surya OCR.
# Activate the conda environment
conda activate trendy_post_mcp
# Run the MCP server
python server.py
Usage 📋
Once the server is running, it can be used as an MCP service that provides functions for:
- Processing screenshots 📸
- Analyzing image content 🔍
- Generating trending social media posts in the style of Xiaohongshu 📱
MCP Functions
The server exposes the following MCP functions:
process_screenshot: Extract text from an image URL 🔤generate_post: Create a Xiaohongshu post from image analysis data ✍️process_and_generate: Combine both functions in one step (recommended) 🔄health_check: Check if the server is running properly 🩺
Project Structure 📁
server.py: Main MCP server implementationimage_processor.py: Screenshot processing and OCR functionalitypost_generator.py: Xiaohongshu post generation logicrequirements.txt: Python dependencies
Dependencies 📦
OCR Engine
This project uses Surya OCR for text extraction, which is licensed under the GPL-3.0 License. Surya is a powerful OCR engine that supports multiple languages and provides excellent results for complex layouts.
⚠️ Important License Note: As Surya is licensed under GPL-3.0, any distribution of this software must comply with the GPL-3.0 license terms. Please ensure you understand these terms if you plan to distribute or modify this software.
Other Dependencies
- FastMCP: For MCP server implementation
- Pydantic: For data validation
- Pillow: For image processing
- ZhipuAI: For LLM-based content generation
License 📄
This project is licensed under the MIT License - see the LICENSE file for details. (Note: Components like Surya OCR have their own licenses as mentioned above)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.