The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
🚀 ConnectAI — Model Context Protocol (MCP) Integration Hub
ConnectAI is a GenAI application that demonstrates how Model Context Protocol (MCP) can connect an AI model with external tools and enterprise-style data sources.
The project uses Google Gemini with an MCP client-server architecture to discover and interact with external tools such as Slack, GitHub, and PostgreSQL.
Key Features
MCP Client & Server architecture
AI-powered tool calling
MCP tool discovery
External tool integration
API communication and handshakes
Interactive Streamlit interface
Integration of Gemini with external systems
Tech Stack
Python · Streamlit · Google Gemini API · MCP SDK · Slack · GitHub · PostgreSQL
Key Concepts
MCP · Tool Calling · Client-Server Architecture · Tool Discovery · LLM Integration · API Integration · GenAI
This project helped me understand how MCP can act as a bridge between AI models and external tools, enabling more modular and extensible AI applications.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
AI Property Maintenance Automation
AI-powered property maintenance automation designed to streamline how property management teams handle tenant maintenance requests.
The system takes a maintenance request, analyzes the issue, determines its priority and category, recommends a suitable vendor, and automatically creates a structured work order.
Workflow:
Tenant request → AI analysis → Priority & category → Vendor matching → Work order
Built with: Python, Flask, SQLite, HTML, CSS, JavaScript, and AI-assisted request classification.
This project was built as a portfolio demonstration of AI automation for property management operations.
Turning a tenant request into a ready work order in seconds removes the manual triage step.
Built an AI-powered Social Media Post Analyzer that analyzes social media content and generates structured insights using LLMs.
The application uses LangChain and Pydantic to process the input and return structured results through an interactive Streamlit interface.
Built with: Python, LangChain, Pydantic, Hugging Face, Streamlit, and LangSmith.
Pydantic catches shape errors, but a plausible wrong insight can still pass. I'd keep a small set of posts with expected labels in LangSmith and rerun it after prompt changes. Are you tracking that kind of drift?
• Oct 3
AIChat is an AI-powered web application for chatting, document analysis, image generation, and coding assistance. I focused on creating a clean, responsive interface with simple navigation and a smooth user experience across different AI tools.
Nice to see the interface stay clean while juggling chat, docs and images, that smooth navigation really cuts the friction for users.