
Wems
io.github.heliosarchitectPublished by GitHub account heliosarchitectv1.5.3Updated Oct 24, 2026
Real-time natural hazard monitoring: earthquakes, tsunamis, volcanoes, solar weather, air quality
Overview
A local MCP server that gives an assistant live natural-hazard data: earthquakes, tsunamis, volcanoes, space weather, storms, air quality and threat advisories.
- What you can do
- Query recent earthquakes, tsunamis, volcanoes and drought status by region or threshold, with magnitude and alert-level filtering for earthquakes and volcanoes and US state drought levels for drought status. Check space weather and solar activity, including K-index, flares, CMEs and active NOAA alerts. Track hurricanes, wildfires, severe weather and floods, including forecast tracks, fire perimeters and river gauge data. Read air quality indexes with pollutant breakdowns and threat advisories covering terrorism, travel risk and cyber threats. Adjust alert thresholds and webhook endpoints, and optionally fuse incidents across several sources.
- When to use it
- Useful when an assistant needs current, authoritative hazard information for risk assessment, news reporting, research or location-specific safety monitoring, or when you want critical events pushed to a webhook.
- Requirements
- Runs locally as a Python package (wems-mcp-server) via pip, or from source; Docker is also mentioned. It calls public hazard APIs from USGS, NOAA, NWS, Smithsonian, OpenAQ, DHS, the State Department and CISA, so network access is needed. An optional config file path can be passed through the WEMS_CONFIG environment variable.
Installation
In SourceWeft
- Open Wems in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
🌍 WEMS - World Event Monitoring System
[PyPI version] [License: MIT] [Python 3.8+] [MCP Compatible]
🚨 Real-time Natural Hazard Monitoring for AI Agents
A powerful Model Context Protocol (MCP) server that connects AI assistants to authoritative natural hazard data sources. Monitor earthquakes, tsunamis, volcanoes, and solar events with configurable alerts and webhooks.
🤖 AI Agents: Skip scanning this repo. Read
AI.TOCfirst — it's a 500-token project map. Then useAI.INDEXto find specific functions andAI.REGISTERfor env vars, APIs, and config. This project uses the LBF AI Navigation Standard.
⚡ Key Features
- 🌋 9+ Authoritative Data Sources: USGS, NOAA, Smithsonian GVP, NHC, NIFC, OpenAQ, DHS, State Dept, CISA, US Drought Monitor
- 🎯 Real-time Monitoring: Live data feeds with customizable thresholds
- 🔔 Smart Alerts: Webhook notifications for critical events
- 🗺️ Geographic Filtering: Target specific regions or global coverage
- 🔧 Zero Configuration: Works out-of-the-box, configure only what you need
- 🐳 Production Ready: Docker support, comprehensive error handling
Natural Hazards Covered
🚀 Quick Start
Install via PyPI (Recommended)
Or install from source
Basic Usage
One-command AI Alerting Setup (Relay + n8n)
This will:
- install/start
wems-unified-relay.service - upsert and activate the unified n8n ingest workflow
- wire tracker posting credentials automatically
Example Output
MCP Tools
Configuration
Data Sources
- USGS Earthquake Hazards Program
- NOAA Pacific Tsunami Warning Center
- NOAA Central Tsunami Warning Center
- Smithsonian Global Volcanism Program
- NOAA Space Weather Prediction Center
- National Hurricane Center (NHC)
- National Interagency Fire Center (NIFC)
- NWS Alerts API
- OpenAQ (Global Air Quality)
- DHS National Terrorism Advisory System (NTAS)
- U.S. State Department Travel Advisories
- CISA Cybersecurity Advisories
OpenClaw Integration
Add to your OpenClaw configuration:
🎯 Use Cases
- 🏢 Enterprise Risk Management: Automated threat assessment for global operations
- 📺 News Organizations: Real-time natural disaster reporting and alerts
- 🔬 Research Institutions: Data collection for scientific analysis
- 🏠 Personal Safety: Location-specific hazard monitoring for families
- 🤖 AI Emergency Response: Integration with disaster response chatbots
- 📱 Alert Systems: Custom notification workflows for critical events
🔧 Advanced Configuration
📊 Monitoring Dashboard
Pair with monitoring tools for comprehensive coverage:
💳 Billing & Monetization (Current)
WEMS now includes Stripe metering scaffolding and affordable default pricing.
Current pricing defaults
- Free tier: 5,000 calls per rolling 30 days
- 0–100,000 calls: $0.0010/call
- 100,001–500,000 calls: $0.0008/call
- 500,001+ calls: $0.0006/call
Accessory call weights (default)
- Most tools:
1unit check_space_weather_alerts:2unitsfuse_multi_source_incidents:3units
Billing config
See: config/wems_stripe_billing.json
Key fields:
event_nameapi_key_to_customerbilling_units.defaultbilling_units.by_toolpricing.free_calls_per_rolling_30dpricing.tiers[]
Stripe key source
STRIPE_API_KEYorSTRIPE_SECRET_KEY(direct env)
WEMS uses best-effort lookup and never blocks alerting if billing key resolution fails.
Built with ❤️ for the AI community by Helios 🌞
Part of the expanding OpenClaw ecosystem
Source: README.md at commit 1941432
Tools
0Version history
1- v1.5.3LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts