syedabdulazeez-021/atlas-sentinel

Atlas Sentinel is a real time threat monitoring tool for factories, warehouses, and supply chains, built as an MCP server so that any AI assistant, like Claude or ChatGPT, can use it directly. MCP stands for Model Context Protocol, a way for AI assistants to connect to outside tools and data. Large companies normally pay expensive vendors for this kind of early warning capability, and this project offers a similar idea as an open tool. You register your factories, warehouses, or suppliers with their locations, and then you can ask a connected AI assistant something like what threatens my operations right now. The server checks several live public data sources at once, including real earthquake data from USGS, weather conditions at each site, geomagnetic storm data from NOAA, and general news signals, then returns a ranked summary of possible threats along with suggested actions. It offers twelve tools an AI assistant can call, covering things like registering and listing sites, checking recent earthquakes, finding nearby critical infrastructure, replaying past events for testing, checking weather forecasts, and generating a formal situation report. All of the external data sources it uses are free and do not require an API key. The project is designed to avoid crashing, returning clear error messages instead, and it clearly labels whether information is live real world data or a simulated replay for demonstration purposes. To try it, you install its dependencies and run it in development mode, then connect it to a compatible AI client. It can run locally on your own machine or be deployed so multiple AI clients can reach it over the internet. The README does not state a license for this project, so its usage terms are not specified.