MCP server exposing 3 tools for openfema.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/openfema/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}disaster_declarations — Look up and COUNT US federal disaster declarations (FEMA DisasterDeclarationsSummaries). Filters: state (2-letter), incidentType (e.g. 'Fire', 'Flood', 'Hurricane', 'Severe Storm'), declarationType ('DR' major disaster, 'EM' emergency, 'FM' fire management), year (fyDeclared, the federal FISCAL year), and since/until for a real calendar date range — use since/until for questions like 'in the past year', which a fiscal year does not answer. Counts are DISTINCT DISASTERS by default, not table rows: FEMA publishes one row per disaster per designated county, so Hurricane Harvey is ~60 rows for Texas but one declaration. Pass designatedArea or grain:'area' for county-level rows. Returns the most recent first.query_dataset — Generic OData query against any OpenFEMA dataset. Specify the entity name (and optionally version; defaults to the verified current version) plus OData params: filter, select, orderby, top, skip. Use list_datasets to see available entities/versions and the filter syntax. Returns { metadata, records }.list_datasets — List the OpenFEMA datasets this pack knows about, with their entity name, current version, and a description. Also documents the OData filter syntax and response shape. Call this first to discover what query_dataset can target.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/openfema/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io