Overview

Federal disaster recovery data from FEMA: disaster declarations, public assistance grants, individual housing assistance, and NFIP flood insurance claims. Search declarations by state or incident, see the public and housing assistance behind any disaster, and run SQL over large flood-claim result sets.

Tools

fema_dataframe_drop is opt-in: it appears in tools/list only when FEMA_ENABLE_CANVAS_DROP=true. The other eight tools are always listed.

Resources

All resource data is also reachable via tools. Use fema_get_disaster for designated-area detail (up to 1,000 rows).

Capability reference

fema_search_disasters _tool

• Filters: state, incident_type, declaration_type (DR/EM/FM), inclusive date_from/date_to (YYYY-MM-DD), and county. incident_type and county are case-insensitive substring matches. Page with limit (1–1000, default 50) and offset; a page stops at 100,000 characters and next_offset says where to resume.
• Returns one summary per disaster number with designated_area_count, program flags, and declaration totals. With county, total_area_rows and matched_areas (FIPS codes and per-area flags) show the matching areas. Errors: invalid_state, invalid_range (date_from after date_to), request_too_long.
• Searches the most recent 10,000 designated-area rows. When capped, results are marked truncated, totals are lower bounds, and notice names the next date_to.

fema_get_disaster _tool

• Requires disaster_number from fema_search_disasters.
• Returns up to 1,000 designated-area records, FIPS codes, incident period, and program flags combined across fetched areas; a missing disaster returns not_found. When more rows exist, areas_truncated, total_designated_area_count, and notice disclose partial coverage. False flags do not exclude programs in unfetched rows; use fema_query_dataset for the full declaration.

fema_get_public_assistance _tool

• Requires disaster_number or state; optional county (case-insensitive substring), limit (1–10000, default 100), and offset. A page stops at 100,000 characters; next_offset says where to resume.
• Returns applicants, damage categories, project size/status, and federal and total obligations. Errors: invalid_state, missing_filter, not_found, request_too_long.

fema_get_housing_assistance _tool

• Requires disaster_number; optional state, county (case-insensitive substring), zip_code (5 digits), type (owners/renters/both, default both), limit (1–10000, default 100), and offset. A page stops at 100,000 characters; one next_offset continues both owners and renters.
• Returns separate owners and renters arrays with county/ZIP registrations, approved amounts, and inspection counts, plus owners_count/renters_count. Owners also carry inspected damage in USD; renters carry damage-degree counts only. Errors: invalid_state, not_found, request_too_long.

fema_search_nfip _tool

• Requires state; optional county_code (5-digit FIPS like 48201, or a 3-digit code like 201 that gets the state prefix), zip_code, year_from/year_to, limit (1–10000, default 1000), and offset. Results come newest loss first.
• Inline claims stop at 100,000 characters; next_offset and notice say how to continue. Errors: invalid_state, invalid_county_code (anything but 1–5 digits, or a short code for FM, MH, or PW), invalid_range (year_from after year_to).
• County searches check for claims without a county code across the same state/year range, using one count-only exchange with no retries and a two-second deadline. The response uses the count only if ready with the primary page; otherwise it says coverage was not checked. These claims cannot be allocated to the selected county or ZIP. Removing county_code and optionally searching known ZIPs may help; ZIP results are not guaranteed complete or equivalent to a county.
• With CANVAS_PROVIDER_TYPE=duckdb, a first-page match over the inline limit stages up to 50,000 rows. canvas_id, canvas_table, and staged_count identify the stage, truncated: true marks its cap, and total_count is the full match. Inspect it with fema_dataframe_describe, then query it with fema_dataframe_query.

fema_dataframe_describe _tool

• Requires canvas_id from fema_search_nfip.
• Lists table/view names, column types, nullability, and staged row counts. Typed errors: canvas_not_found, canvas_unavailable.

fema_dataframe_query _tool

• Requires canvas_id and a single SQL query; only SELECT is allowed.
• Rows are capped at the canvas row limit and 100,000 characters; truncated/shown and OFFSET guidance appear when the result is cut. Errors: canvas_unavailable, canvas_not_found, missing_table, invalid_sql, non_select_statement, multi_statement, denied_function, plan_operator_not_allowed, sql_read_only, sql_execution_error (use TRY_CAST or filter incompatible values).

fema_dataframe_drop _tool

• Requires canvas_id and the exact table_name from fema_dataframe_describe.
• Removes one staged table or view; dropped: false means the name did not exist. Errors: canvas_not_found, canvas_unavailable.
• Opt-in through FEMA_ENABLE_CANVAS_DROP=true.

fema_query_dataset _tool

• Requires a case-sensitive OpenFEMA dataset; optional OData filter/select/orderby, limit (1–10000, default 100), and offset. A page stops at 100,000 characters; next_offset says where to resume.
• Returns records and total_count. Errors: unknown_dataset, dataset_not_served, catalog_unavailable (retryable), invalid_filter, invalid_select, invalid_orderby, invalid_odata_syntax, request_too_long (URL past about 8,900 characters), filter_too_complex (nested more than 100 levels).
• For a list of values, use field in ('a','b') instead of chained or comparisons (about 90 allowed). For NfipPolicies, use propertyState and reportedZipCode, and always include a ZIP filter to avoid timeout.

fema://disaster/{disasterNumber} _resource

• Requires disasterNumber as a string of digits.
• Returns title, state, incident type, declaration type/date, incident period, programs_declared, and fetched designated_area_count (up to 500). When more rows exist, the summary includes areas_truncated, total_designated_area_count, and notice: programs describe only fetched rows, and an empty list does not establish absence. Use fema_query_dataset for full rows. not_found points to fema_search_disasters.

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

OpenFEMA-specific:

• Case-insensitive county and incident type filters, using bundled declaration names plus exact PA county spellings. Refresh with bun run vocabulary:build: sequential full exports read declarations in ID order and nonnull PA counties without a sort, with bounded transient retries. Each export must match its reported count; a failed or incomplete refresh leaves the snapshot unchanged.
• DisasterDeclarationsSummaries rows collapse to one summary per declaration, with designated_area_count
• fema_search_nfip requires state, which prevents unbounded 2.7M-row fetches
• Large NFIP result sets spill into DuckDB tables you can query with SQL via DataCanvas
• No API keys required — OpenFEMA is a free, public API

Agent-friendly output:

• Disaster number is the join key across tools, so calls chain without re-searching
• Empty searches return empty arrays, zero totals, and a notice with guidance for supplied filters on both response surfaces; assistance calls can check declared programs with fema_get_disaster. Paging past a nonzero total has separate offset guidance.
• Typed errors on every tool (invalid_state, invalid_county_code, invalid_range, not_found, missing_filter, unknown_dataset, dataset_not_served, invalid_filter, invalid_select, invalid_orderby, invalid_odata_syntax, request_too_long, filter_too_complex, canvas_unavailable), each with a recovery hint
• designated_area_count on search results shows whether fema_get_disaster is worth a follow-up

Getting started

Public Hosted Instance

A public instance is available at https://fema.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "fema-mcp-server": {
      "type": "streamable-http",
      "url": "https://fema.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "fema-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/fema-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "fema-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/fema-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "fema-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/fema-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

To enable DuckDB-backed SQL analytics for NFIP Claims:

{
  "mcpServers": {
    "fema-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/fema-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "CANVAS_PROVIDER_TYPE": "duckdb"
      }
    }
  }
}

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).
• No API keys required — OpenFEMA is a free, public API.
• Optional: set CANVAS_PROVIDER_TYPE=duckdb to enable SQL analytics over large NFIP Claims result sets.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/fema-mcp-server.git

2. Navigate into the directory:

cd fema-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env — no required vars, but CANVAS_PROVIDER_TYPE=duckdb enables SQL analytics

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  shCopy

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  shCopy

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t fema-mcp-server .
docker run --rm -e MCP_TRANSPORT_TYPE=stdio fema-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/fema-mcp-server. OpenTelemetry peer dependencies are installed by default; build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Register new tools and resources in src/index.ts
• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

Data source

Data is provided by the OpenFEMA API, a free public API maintained by the Federal Emergency Management Agency. Usage is subject to OpenFEMA Terms and Conditions.

This product uses the Federal Emergency Management Agency's OpenFEMA API, but is not endorsed by FEMA. The Federal Government or FEMA cannot vouch for the data or analyses derived from these data after the data have been retrieved from the Agency's website(s).

When citing OpenFEMA datasets in research or publications, use the format FEMA specifies:

Federal Emergency Management Agency (FEMA), OpenFEMA Dataset: <name>. Retrieved from <URL> on <date>.

License

Apache-2.0 — see LICENSE for details.