nfip-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@nfip-mcp-server What are the total flood insurance payouts in Texas?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
nfip-mcp-server
An MCP (Model Context Protocol) server exposing real US flood insurance claims data — sourced live from FEMA's public OpenFEMA API — as tools an AI agent can call: claim lookup, filtered search, aggregate stats, and flood event summaries.
Why this exists
Built as a hands-on project to learn MCP server design against a real, non-trivial dataset rather than mock data — the same pattern used to expose proprietary data (claims, policies, internal knowledge bases) to enterprise AI agents.
Real data — pulled directly from FEMA's OpenFEMA API, no key required, redacted for privacy, no PII.
Tested — unit tests against the query layer, integration tests against the real server subprocess, CI running both on every push.
Deployable — pip-installable package, Dockerfile included.
Related MCP server: fema-nfhl-mcp
Available Tools
Tool | Description |
| Look up a single flood claim by its unique ID |
| Filtered search by state, flood event, minimum building payment, and/or year |
| Aggregate stats (count, total/average payments, year range), optionally by state |
| Distinct named flood events in the data with claim counts |
Architecture
nfip-mcp-server/
├── src/nfip_mcp/
│ ├── db.py ← pure query functions (no MCP dependency, easy to unit test)
│ └── server.py ← FastMCP tool wrappers around db.py, entry point
├── data/
│ ├── nfip_raw.json ← real claims data pulled from the OpenFEMA API
│ └── claims.db ← SQLite database built from the raw data
├── scripts/
│ ├── build_db.py ← loads nfip_raw.json into claims.db
│ ├── fetch_more_data.py ← pulls a larger, filtered dataset from the live API
│ └── demo_client.py ← manual walkthrough of every tool
├── tests/
│ ├── test_db.py ← unit tests against the query layer
│ └── test_integration.py ← spins up the real server and calls it over stdio
└── .github/workflows/ci.ymlThe query logic in db.py is deliberately free of any MCP-specific code —
it's plain functions taking a sqlite3.Connection and returning dicts, so
it's testable without spinning up a server or client. server.py just wires
thin @mcp.tool() wrappers around it.
Setup
git clone https://github.com/YOUR-USERNAME/nfip-mcp-server
cd nfip-mcp-server
pip install -e ".[dev]"
python scripts/build_db.pyRunning the tests
pytest tests/ # everything
pytest tests/test_db.py # fast unit tests only
pytest -m integration # slower, spins up the real server subprocessRunning the server
nfip-mcp-server # after pip install, runs over stdio
# or
python -m nfip_mcp.serverTo see it working interactively without a full MCP host installed:
python scripts/demo_client.pyConnecting to Claude Desktop (or another MCP host)
Add to your MCP host's config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"nfip-claims": {
"command": "nfip-mcp-server"
}
}
}Running with Docker
docker build -t nfip-mcp-server .
docker run -i nfip-mcp-serverPoint your MCP host's command at docker run -i nfip-mcp-server to use
the containerized version instead.
Scaling up the data
The bundled data/claims.db has a small (~24 record) real sample, enough
to prove the pipeline end to end. To pull a much larger, properly filtered
slice of the real data (this defaults to flood-prone Northeast states):
python scripts/fetch_more_data.py
python scripts/build_db.pyLicense
MIT — see LICENSE.
Available Tools
4 toolsclaims_summaryA
Get aggregate statistics across claims, optionally filtered to one state.
Args: state: Two-letter US state code to filter by. Omit for all states.
Returns: Claim count, total and average building payments, and the earliest/latest loss years in scope.
Inputs: state.
get_claimA
Look up a single NFIP flood claim by its unique claim ID.
Args: claim_id: The claim's unique identifier (UUID string).
Returns: The full claim record, or an error message if not found.
Inputs: claim_id (required).
list_flood_eventsA
List the distinct named flood events present in the claims data (e.g. 'Hurricane Katrina', 'Tropical Storm Allison'), with claim counts.
Returns: A dict mapping each flood event name to its claim count.
Inputs: no named parameters.
search_claimsA
Search NFIP flood claims with optional filters. All filters are combined with AND; omit any filter you don't need.
Args: state: Two-letter US state code, e.g. 'FL', 'NJ'. flood_event: Substring match against the named flood event, e.g. 'Katrina' matches 'Hurricane Katrina'. min_building_payment: Only return claims where the net building payment was at least this amount. year: Year the loss occurred. limit: Max number of results to return (default 10).
Returns: A dict with the matching claims and how many were found.
Inputs: year, limit, state, flood_event, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: listing flood events, retrieving a single claim, searching claims by filters, and producing aggregate statistics. There is minimal overlap in functionality, and descriptions make the boundaries obvious.
Three tools follow a consistent verb_noun pattern: list_flood_events, get_claim, and search_claims. claims_summary breaks the pattern by using a noun phrase, though it is still clear and readable.
Four tools is a well-scoped size for a read-only NFIP claims data server. Each tool covers a distinct query need without redundancy or bloat.
The surface covers the core read-only workflows: enumeration, single-record lookup, filtered search, and aggregate statistics. Minor gaps exist, such as summary filtering by flood event or year, but these do not create dead ends for common use cases.
Maintenance
Related MCP Connectors
OpenFEMA MCP — US Federal Emergency Management Agency open data.
An MCP server that provides congressional transcripts
This MCP server provides seamless access to Malaysia's government open data, including datasets, w…
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that gives AI agents clean, token-efficient access to US civic & property data — geocoding, census tracts, Opportunity Zones, ACS demographics, and FEMA flood zones — sourced entirely from free federal open data.51MIT
- AlicenseAqualityDmaintenanceAn MCP server that gives AI assistants direct access to the FEMA National Flood Hazard Layer (NFHL) for flood zone lookups, FIRM panel information, and flood map data in the United States.69 npmMIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that gives AI agents grounded access to US natural-hazard data — weather alerts, forecasts, earthquakes, and FEMA flood zones — from free, keyless US government APIs.MIT
- FlicenseNot gradedqualityCmaintenanceRemote MCP server exposing US Census (ACS 5-year) and FEMA flood data. Works as a connector in both Claude and ChatGPT.-