Project Info
Inspiration
I am a civil engineer, and I have seen construction records managed through WhatsApp, notebooks, bills, and phone calls. This makes it difficult to track materials, labour, payments, site work, and project progress. I built CMT MCP to make construction management easier through ChatGPT.
What it does
CMT MCP lets users manage construction projects by simply chatting with ChatGPT. Users can add and view materials, labour, payments, daily site logs, issues, photos, documents, checklists, and project tasks. For example: Add 50 bags of cement at Rs. 850 per bag. Or: Show me this project’s total material and labour cost. How I built it I built an MCP server and connected it to a separate development Supabase account for this demo. This keeps the demo environment separate from the production app and allows ChatGPT to safely read and manage test construction records. Challenges I faced The main challenge was turning normal construction language into clear and correct records. I also had to make sure users could only access projects they had permission to view. Accomplishments I am proud of I built a working MCP that can manage real construction workflows through ChatGPT. It can handle materials, labour, payments, site logs, issues, photos, documents, project members, schedules, and reports. What I learned I learned how MCP can turn ChatGPT into a useful tool for real industries.
What's next
Next, I want to improve bill reading, photo uploads, voice entry, automatic reports, budget comparison, and Nepali language support. My goal is to make construction tracking simple and accessible through ChatGPT.
This project did not link a GitHub repository.
Analysis
No indexed repository for this project, so there are no commit stats to show.
Technology
- SupabaseUnchecked
No repository was indexed for this project, so these Devpost claims have not been checked against code.
AI coding agents
No repository was indexed, so agent usage could not be checked.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
No repository was indexed, so there is no codebase to measure.
This project did not link a GitHub repository, so there is nothing to diagram.
This project did not link a GitHub repository, so its feature claims have not been checked against code.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.