About Property Hazard MCP
Property Hazard MCP assesses natural-hazard exposure for a single US property address using public data without API keys. It returns hazard measurements and a deterministic score, while marking unavailable data as unknown.
Key features
- 01Address validation and geocoding
- 02Flood-zone lookup
- 03Wildfire hazard scoring
- 04Seismic PGA and proximity data
- 05Deterministic score, tier, and drivers
Use cases
- 01Review hazard exposure for a US property
- 02Compare flood, wildfire, and seismic indicators
- 03Identify hazard fields unavailable from data sources
MCP support
The remote MCP server exposes the `assess_property_hazard` tool. Given a US address, it returns flood, wildfire, seismic, fault-distance, and coastal-proximity data with an overall hazard score.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.zipquote.ai/mcpclaude mcp add --transport http ai-zipquote-us-property-hazard-risk https://mcp.zipquote.ai/mcp{"mcpServers":{"ai-zipquote-us-property-hazard-risk":{"type":"http","url":"https://mcp.zipquote.ai/mcp"}}}Open in Cursor{"servers":{"ai-zipquote-us-property-hazard-risk":{"type":"http","url":"https://mcp.zipquote.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-zipquote-us-property-hazard-risk":{"type":"http","url":"https://mcp.zipquote.ai/mcp"}}}{"mcpServers":{"ai-zipquote-us-property-hazard-risk":{"serverUrl":"https://mcp.zipquote.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
1| Parameter | Type | Required | Description |
|---|---|---|---|
| address | string | Yes |
Details
From the project READMEus-property-hazard-risk (MCP server)
A remote MCP server that assesses natural hazard exposure — flood, wildfire, earthquake, and coastal proximity — for a single US property address, using only free, keyless public data. No API keys, no database, no map. Works from Claude, ChatGPT, or any other MCP-compatible host.
Tool
assess_property_hazard(address: str)
Validates and geocodes the address, then returns flood zone (FEMA NFHL),
wildfire hazard score, seismic PGA (USGS, ASCE 7-22), fault and coastal
distance, and a deterministic 0–100 hazard_score / hazard_tier with up to
5 hazard_drivers. If a data source is unavailable, that field is reported
as unknown rather than assumed zero-risk.
Data sources
- US Census Bureau Geocoder — address validation + geocoding
- FEMA NFHL — flood zone
- USGS Design Maps — seismic PGA
- Static reference points (haversine) — fault + coastal proximity
Local dev
python -m venv venv
venv/Scripts/pip install -r requirements.txt # venv/bin/pip on macOS/Linux
cd src
../venv/Scripts/python server.py # ../venv/bin/python on macOS/Linux
Starts a streamable-HTTP MCP server on http://localhost:8000/mcp:
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"assess_property_hazard","arguments":{"address":"1600 Pennsylvania Ave NW, Washington, DC 20500"}}}'
Deployment
Runs via Docker Compose (docker-compose.yml):
docker compose up -d --build
Known limitations
- US addresses only
- FEMA NFHL is occasionally unreachable from some networks (
flood_available: false) - Wildfire scoring is a coarse coordinate-zone heuristic, not parcel-level
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.