GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Description from the maker (original English)
Real-time natural hazard monitoring: earthquakes, tsunamis, volcanoes, solar weather, air quality
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"wems": {
"command": "uvx",
"args": [
"wems-mcp-server"
]
}
}
}Run this in your terminal
claude mcp add wems -- uvx wems-mcp-serverPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"wems": {
"command": "uvx",
"args": [
"wems-mcp-server"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"wems": {
"type": "stdio",
"command": "uvx",
"args": [
"wems-mcp-server"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account heliosarchitect, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.5.3) reached the registry 9 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
🚨 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.
| Hazard Type | Data Source | Coverage |
|---|---|---|
| 🌊 Earthquakes | USGS | Global, magnitude filtering |
| 🌊 Tsunamis | NOAA PTWC + CTWC | Global ocean basins |
| 🌋 Volcanoes | Smithsonian GVP + USGS | Global volcanic activity |
| ☀️ Solar Events | NOAA SWPC | Solar flares, CMEs, geomagnetic storms |
| 🌞 Space Weather Alerts | NOAA SWPC | Active space weather alerts & warnings |
| 🌀 Hurricanes | NHC + NWS | Atlantic & Pacific tropical cyclones |
| 🔥 Wildfires | NWS + NIFC | Fire weather alerts & active perimeters |
| ⛈️ Severe Weather | NWS Alerts | Tornadoes, thunderstorms, floods, winter storms |
| 💨 Air Quality | OpenAQ | Global AQI, PM2.5, PM10, O₃, NO₂, SO₂, CO |
| 🌵 Drought Conditions | US Drought Monitor | US state drought levels (D0-D4) + trends |
| 🛡️ Threat Advisories | DHS NTAS + State Dept + CISA | Terrorism, travel risk, cyber threats |
pip install wems-mcp-server
git clone https://github.com/heliosarchitect/wems-mcp-server.git
cd wems-mcp-server pip install -r requirements.txt
# Run as MCP server (connects to AI assistants)
python -m wems_mcp_server
python -c " import asyncio from wems_mcp_server import check_earthquakes print(asyncio.run(check_earthquakes(min_magnitude=6.0))) "
bash scripts/setup_wems_alerting_ai.sh
This will:
wems-unified-relay.service{
"earthquakes_found": 3, "events": [ { "magnitude": 7.2, "location": "67 km SW of Tres Picos, Mexico", "time": "2024-02-13T14:30:15Z", "depth": 35.8, "tsunami_threat": true } ] }
| Tool | Description |
|---|---|
check_earthquakes | Query recent earthquake activity |
check_solar | Monitor space weather (K-index, flares, CMEs) |
check_volcanoes | Track volcanic activity alerts |
check_tsunamis | Monitor tsunami warnings |
check_hurricanes | Track tropical cyclones & forecast tracks |
check_wildfires | Fire weather alerts & active perimeters |
check_severe_weather | Monitor tornadoes, thunderstorms, flash floods |
check_floods | Flood warnings & USGS river gauge data |
check_air_quality | AQI monitoring with pollutant data |
check_threat_advisories | Terrorism, travel risk & cyber threat monitoring |
check_space_weather_alerts | Active space weather alerts & warnings from NOAA SWPC |
check_drought_status | US state drought conditions with D0-D4 levels (Premium) |
configure_alerts | Update alert thresholds and webhooks |
fuse_multi_source_incidents | Multi-source incident fusion (feature-flagged) |
alerts:
earthquake: min_magnitude: 6.0 regions: ["US", "Caribbean", "Pacific"] webhook: "https://your-endpoint.com/earthquake"
solar: min_kp_index: 7 # Geomagnetic storm threshold webhook: "https://your-endpoint.com/solar"
volcano: alert_levels: ["WARNING", "WATCH"] webhook: "https://your-endpoint.com/volcano"
tsunami: enabled: true regions: ["pacific", "atlantic", "indian"] webhook: "https://your-endpoint.com/tsunami"
Add to your OpenClaw configuration:
{
"mcpServers": { "wems": { "command": "python3", "args": ["/path/to/wems-mcp-server/wems_mcp_server.py"], "env": { "WEMS_CONFIG": "/path/to/config.yaml" } } } }
# config.yaml - Full customization example
alerts: earthquake: min_magnitude: 6.0 regions: ["US", "Caribbean", "Pacific"] webhook: "https://your-endpoint.com/earthquake"
solar: min_kp_index: 7 # G3+ geomagnetic storm webhook: "https://your-endpoint.com/solar"
volcano: alert_levels: ["WARNING", "WATCH"] regions: ["Cascade Range", "Ring of Fire"] webhook: "https://your-endpoint.com/volcano"
tsunami: enabled: true regions: ["pacific", "atlantic", "indian"] webhook: "https://your-endpoint.com/tsunami"
Pair with monitoring tools for comprehensive coverage:
# Example: Send earthquake data to monitoring system
curl -X POST https://your-monitoring.com/api/events \ -H "Content-Type: application/json" \ -d "$(python -c 'import wems; print(wems.get_recent_earthquakes())')"
WEMS now includes Stripe metering scaffolding and affordable default pricing.
1 unitcheck_space_weather_alerts: 2 unitsfuse_multi_source_incidents: 3 unitsSee: config/wems_stripe_billing.json
Key fields:
event_nameapi_key_to_customerbilling_units.defaultbilling_units.by_toolpricing.free_calls_per_rolling_30dpricing.tiers[]STRIPE_API_KEY or STRIPE_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*