Tools

Eight tools are advertised by default. Setting FEMA_ENABLE_CANVAS_DROP=true adds a ninth, destructive DataCanvas cleanup tool. Together they cover the OpenFEMA data surface — convenience tools for the headline datasets, SQL analytics over large NFIP result sets via DuckDB canvas, and a generic escape hatch for datasets the convenience tools don't cover:

fema_search_disasters

The primary entry point — "what disasters were declared in Texas in 2025?"

• Filter by state (2-letter code), incident type (Hurricane, Flood, Wildfire, etc.), declaration type (DR/EM/FM), date range, and county
• Returns deduplicated declaration-level summaries — one row per declaration, not per designated area
• Includes disaster number (the join key for PA and housing tools), title, state, incident type, declaration/incident dates, programs declared (IA/PA/HM), and designatedAreaCount
• Paginated via limit / offset

fema_get_disaster

Fetch all designated-area records for a specific FEMA disaster number.

• Returns every county/municipality row for the declaration with programs activated, incident period, and FIPS codes
• Use after fema_search_disasters to drill into a specific event; the disaster number chains to PA and housing tools
• DisasterDeclarationsSummaries returns one row per designated area — a single declaration can span dozens of counties

fema_get_public_assistance

Retrieve PA funded project details — where federal recovery money went after a disaster.

• Filter by disaster_number, state, or county; at least one of disaster_number or state is required
• Returns applicant, damage category, project size/status, federal share obligated, and total obligated
• Useful for journalists, researchers, and oversight analysts tracking federal grant flows

fema_get_housing_assistance

Individual assistance housing data for a disaster, broken down by county and ZIP.

• Returns owner and renter breakdowns via type param (owners/renters/both)
• Fields include valid registrations, total inspected, total damage, approved IHP amounts, repair/rental/other-needs amounts, and max grants
• Covers HousingAssistanceOwners and HousingAssistanceRenters datasets in a single call

fema_search_nfip

NFIP flood insurance claims with optional DuckDB-backed SQL analytics for large result sets.

• Requires at minimum a state filter — unfiltered NFIP Claims is 2.7M rows
• Additional filters: county_code, zip_code, year_from, year_to; pagination via limit
• When CANVAS_PROVIDER_TYPE=duckdb is set and results exceed the inline cap, the full result set spills to a DataCanvas table and returns a canvas_id handle
• Use fema_dataframe_describe to inspect the schema, then fema_dataframe_query for aggregation, grouping, and time-series analysis without re-fetching

fema_dataframe_describe / fema_dataframe_query / fema_dataframe_drop

In-conversation SQL analytics over NFIP Claims data staged by fema_search_nfip on a DuckDB-backed DataCanvas.

• fema_dataframe_describe: lists columns, types, and row count for a canvas table — use before writing a query
• fema_dataframe_query: runs a single SELECT statement against the staged table; standard DuckDB SQL (GROUP BY, SUM, window functions, time-series)
• fema_dataframe_drop: removes one staged table or view; disabled by default and enabled with FEMA_ENABLE_CANVAS_DROP=true
• Workflow: fema_search_nfip (with canvas enabled) → fema_dataframe_describe → fema_dataframe_query
• SQL queries are read-only — writes, DDL, and DROP statements are rejected by the framework SQL gate. The gated drop tool only removes staged canvas data and never changes FEMA source data.

fema_query_dataset

Generic OData query against any OpenFEMA v2 dataset — the escape hatch for datasets the convenience tools don't cover.

• Accepts raw $filter, $select, $orderby, limit, and offset params
• Dataset name must match an actual OpenFEMA endpoint (e.g. FimaNfipPolicies, IndividualAssistanceHousingRegistrantsLargeDisasters)
• Validates that the API returns JSON (Content-Type check) and surfaces structured error codes on 400 responses

Resources and prompts

All resource data is also reachable via tools. Use fema_get_disaster for the same data with pagination and full designated-area detail.

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool, resource, and prompt definitions — single file per primitive, framework handles registration and validation
• Unified error handling — handlers throw, framework catches, classifies, and formats
• Pluggable auth: none, jwt, oauth
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

FEMA/OpenFEMA-specific:

• Typed OpenFEMA REST client with OData parameter building (%24-encoded to satisfy Akamai's Drupal layer), response parsing, and structured error classification (JSON 400 vs HTML 404)
• Automatic deduplication of DisasterDeclarationsSummaries — one row per designated area collapsed to declaration-level summaries with designatedAreaCount
• NFIP Claims guard: state filter is required to prevent unbounded 2.7M-row fetches
• DataCanvas spillover for NFIP analytics — large NFIP result sets materialize as DuckDB tables queryable via SQL without re-fetching
• No API keys required — OpenFEMA is a free, public API

Agent-friendly output:

• Disaster number is the explicit join key across all datasets — every tool that touches a disaster surfaces it prominently so agents can chain calls without re-searching
• Typed error contracts on every tool — invalid_state, no_results, missing_filter, unknown_dataset, invalid_filter, canvas_unavailable — with recovery hints telling agents the concrete next step
• designatedAreaCount on search results so agents know whether to drill in with fema_get_disaster without having to fetch the full record first

Getting started

Public Hosted Instance