US Government Data

gov-data-mcp

123 US government open-data tools, as one MCP server.

EPA, FEMA, USGS, NOAA, FAA, USACE, FDIC, HUD, NRCS, HRSA, CMS, county assessor rolls and state licensing boards — all reachable as agent-callable tools, all reading directly from official government APIs and bulk files. No scraping, no HTML parsing, no rate-limit roulette.

mcp-name: io.github.malonestar/gov-data-mcp

npx gov-data-mcp

Install

You need a free Apify API token from console.apify.com/settings/integrations. Apify's free tier includes monthly platform credit that covers evaluating every tool here.

Claude Desktop / Claude Code / Cursor

{
  "mcpServers": {
    "gov-data": {
      "command": "npx",
      "args": ["-y", "gov-data-mcp"],
      "env": { "APIFY_TOKEN": "apify_api_..." }
    }
  }
}

Claude Desktop reads claude_desktop_config.json; Claude Code reads .mcp.json in your project; Cursor reads .cursor/mcp.json. The block is identical in all three.

What you get

12 dedicated tools for the highest-traffic questions, callable directly:

Plus three tools that reach the other 111:

• search-gov-data-tools — find a tool by keyword, agency or topic
• describe-gov-data-tool — full input schema for any tool in the catalog
• run-gov-data-tool — run any tool in the catalog

The catalog is bundled, so discovery costs nothing. Ask your agent "what government data tools do you have for flood risk?" and it will search all 123.

Vertical presets

The full server is the right default for a general-purpose agent. For an agent that serves one kind of buyer, a preset narrows the whole surface — the named tools and what search-gov-data-tools / describe-gov-data-tool / run-gov-data-tool can reach — to one shelf, and announces itself to the client under its own server name and description. Same package, same catalog, same release; nothing to install separately. Pass --preset <name> or set GOV_DATA_MCP_PRESET. An unknown preset name refuses to start rather than guessing. npx gov-data-mcp --list-presets prints the current list as JSON.

phase1-esa — Phase I ESA — Environmental Due Diligence

US government environmental records for Phase I Environmental Site Assessments and property due diligence: EPA Superfund / RCRA / UST / brownfield records at ASTM E1527-21 search distances, state tank and spill registries, historic land use from FRS SIC/NAICS, USGS historical topographic map coverage, NWI wetlands, Clean Water Act §404 surface water, RCRA corrective-action cleanups, orphaned wells, FEMA hazard risk and NFIP flood-loss history, plus a twenty-layer go / caution / no-go site verdict. Every tool reads the official source directly and reports what it could not check as null, never as clear.

11 tools: site-due-diligence-bundle · epa-contaminated-site-screener · historic-land-use-sic-contaminant-screener · state-tank-spill-registry-screener · usgs-historical-topo-records-review · epa-rcra-corrective-action-cleanup-monitor · orphaned-well-proximity-screener · fws-wetlands-proximity-screener · nhd-surface-water-404-screener · fema-nri-county-risk-profile · nfip-flood-loss-risk-screener — plus search-gov-data-tools, describe-gov-data-tool, run-gov-data-tool, scoped to this list.

Claude Desktop (claude_desktop_config.json), Claude Code (.mcp.json) and Cursor (.cursor/mcp.json) all take the same block:

{
  "mcpServers": {
    "gov-data-phase1-esa": {
      "command": "npx",
      "args": ["-y", "gov-data-mcp", "--preset", "phase1-esa"],
      "env": { "APIFY_TOKEN": "apify_api_..." }
    }
  }
}

Or, with the environment variable instead of the flag: "args": ["-y", "gov-data-mcp"] and "env": { "APIFY_TOKEN": "apify_api_...", "GOV_DATA_MCP_PRESET": "phase1-esa" }.

Command line: npx gov-data-mcp --preset phase1-esa

cre-leads — CRE & Local Business Leads — Who Just Changed State

Lead-generation feeds built from official state and county registers: new and pending liquor licenses, verified new business openings from Secretary of State and tax rosters, WARN layoff notices, newly licensed real estate agents, licensed childcare providers with contacts, parcel owner of record, absentee-owner lists, distressed-property signal stacks, NYC deed transfers and landlord registries, city business licenses and professional license verification. Delta modes return only what changed since the last run, so a scheduled agent pays for new leads, not the same roster twice.

12 tools: liquor-license-new-openings-tracker · sos-registry-monitor · warn-layoff-aggregator · realtor-license-roster-delta · childcare-provider-leads · parcel-owner-lookup · absentee-owner-lead-list-builder · distressed-property-signal-stacker · acris-deed-transfer-intel · nyc-landlord-registry-lead-list · city-business-license-leads · license-verifier — plus search-gov-data-tools, describe-gov-data-tool, run-gov-data-tool, scoped to this list.

Claude Desktop (claude_desktop_config.json), Claude Code (.mcp.json) and Cursor (.cursor/mcp.json) all take the same block:

{
  "mcpServers": {
    "gov-data-cre-leads": {
      "command": "npx",
      "args": ["-y", "gov-data-mcp", "--preset", "cre-leads"],
      "env": { "APIFY_TOKEN": "apify_api_..." }
    }
  }
}

Or, with the environment variable instead of the flag: "args": ["-y", "gov-data-mcp"] and "env": { "APIFY_TOKEN": "apify_api_...", "GOV_DATA_MCP_PRESET": "cre-leads" }.

Command line: npx gov-data-mcp --preset cre-leads

compliance — KYB, Sanctions & Financial Compliance Screening

Know-your-business and compliance screening from primary US government registers: company existence across Secretary of State registries, the Trade.gov Consolidated Screening List (OFAC SDN, BIS, State) as a delta, the DHS UFLPA Entity List, state Medicaid and HHS-OIG exclusion lists, professional license verification, GLEIF LEI ownership graphs, FDIC / NCUA institution health, FDIC structure changes, SEC investment-adviser registrations, PCAOB auditor engagements and SEC Regulation CF / A+ offering lifecycles. A screen that could not reach its source fails loudly rather than returning a clean sheet.

12 tools: kyb-company-verifier · consolidated-screening-list-delta · uflpa-entity-list-monitor · medicaid-exclusion-screener · license-verifier · gleif-ownership-graph · fdic-ncua-health-rollup · fdic-structure-change-delta-monitor · ria-registration-delta-monitor · pcaob-auditor-engagement-monitor · reg-cf-lifecycle-monitor · reg-a-plus-lifecycle-monitor — plus search-gov-data-tools, describe-gov-data-tool, run-gov-data-tool, scoped to this list.

Claude Desktop (claude_desktop_config.json), Claude Code (.mcp.json) and Cursor (.cursor/mcp.json) all take the same block:

{
  "mcpServers": {
    "gov-data-compliance": {
      "command": "npx",
      "args": ["-y", "gov-data-mcp", "--preset", "compliance"],
      "env": { "APIFY_TOKEN": "apify_api_..." }
    }
  }
}

Or, with the environment variable instead of the flag: "args": ["-y", "gov-data-mcp"] and "env": { "APIFY_TOKEN": "apify_api_...", "GOV_DATA_MCP_PRESET": "compliance" }.

Command line: npx gov-data-mcp --preset compliance

Example prompts

Screen 1200 Broadway, Denver CO for environmental risk under ASTM E1527-21 and tell me which findings fall inside the standard's search distance.

I'm siting a 40 MW solar project at 41.88, -93.10. Check grid proximity, prime farmland, wetlands, critical habitat and the interconnection queue, then tell me what would kill the project.

Can I fly a Part 107 mission at these six coordinates, and which ones need a DroneZone authorization rather than LAANC?

Which Texas banks show the 2006 CRE-concentration guidance flagged on both prongs?

How it works

Each tool is a published Apify Actor that this server invokes through the Apify API. The server starts the run, waits for a terminal state, and returns the rows.

Billing is to your own Apify account at each actor's published pay-per-result rate, listed on its Store page. Free-tier credit covers evaluation. A run that fails bills nothing beyond a fractional actor-start charge.

Every result carries the run_id and a console.apify.com URL, so any claim an agent makes from this server can be traced back to the exact run that produced it.

No Apify account? Agents can pay per run with x402

Every tool in this catalog is eligible for Apify's agentic payments: an agent with a funded Coinbase Agentic Wallet (USDC on Base, $1 minimum) buys a prepaid Apify token over the x402 protocol and uses it as APIFY_TOKEN — no account, no billing setup, no API key. The ready-made skill is apify.it/x402-awal:

npx -y awal auth login <email>            # one-time wallet auth
npx awal x402 pay 'https://agi.apify.com/protocols/x402/prepaid-tokens?amount=5&currency=usd' --max-amount 5000000 --json
# → returns a bearer token; export it as APIFY_TOKEN and start this server as usual

The prepaid balance is an absolute spending cap and expires after 14 days. Every tool here charges per result or per generated report. None pass platform usage through, none require full permissions, and none run in Standby mode, which are the three things that make an Actor ineligible. Prices are in the catalog (usdPerUnit and priceUnit on every search hit, plus usdPer1000Results for per-row tools), so an agent can see the cost before spending.

Calling the tools well (guide for agents)

The most common way to waste a call is to guess the input: no state, no coordinates, a misspelled field. These tools then refuse the question, or match nothing, and the caller still pays a fractional actor-start fee. The server helps an agent avoid that in four ways:

1. An agent guide in the handshake. The MCP initialize response carries instructions. They cover the search → describe → run workflow, scoping every call, real codes and ISO dates, starting small, and how to read failures, zero rows and null.

2. Verified example inputs. describe-gov-data-tool (free) returns:

   • must_supply: the fields you have to provide.
   • example_input: the actor's prefill, which Apify's own QA runs every few days and which returns rows.
   • Up to two examples: inputs from the actor's published, run-verified demo tasks, each with a human title.

   Start from one of them and change only the values you need.

3. A free local check before any metered run. A missing required field, an input name the tool doesn't have, or a value outside a closed vocabulary is reported with run_status: NOT_RUN_INPUT_INVALID and the example to copy. Nothing runs and nothing is charged.

4. A next step on every unhelpful result. A failed run returns the actor's own reason in note, plus next_step, must_supply and example_input. A zero-row success says to check spelling, state code, radius and date window before concluding that nothing exists.

Example of a well-scoped first call:

{"tool": "medicaid-exclusion-screener", "input": {"mode": "screen", "targets": [{"npi": "1972902351"}, {"name": "Jane Doe", "dob": "1970-01-01"}]}}

On honest answers

These actors are built around one rule: a failure must never be presentable as "nothing was found." That distinction matters most in exactly the cases people use this for — telling a buyer a property is clear of contamination, telling a pilot an airspace is uncontrolled, telling a lender a borrower is unlicensed.

So this server:

• reports run_status on every call, and never attaches a rows key to a run that did not succeed
• distinguishes "the run SUCCEEDED and the source genuinely matched nothing" from "the run failed" in the response text, explicitly
• retries transient Apify 429/5xx, then fails loudly saying the platform failed and no conclusion should be drawn about the government source
• treats an unknown tool name as a catalog miss, never as an empty result

The underlying actors carry the same discipline: per-source status on every row, null meaning not checked rather than checked and negative, live drift assertions that fail the run when an upstream silently truncates, and pagination guards on sources that answer HTTP 200 with a partial payload. Each actor's Store page documents the specific traps it defends against.

Coverage

123 tools, every one reading an official US government API or bulk file. The MCP server exposes 15 of them directly — twelve named tools plus search-gov-data-tools, describe-gov-data-tool and run-gov-data-tool, which reach the rest — because agents choose badly when handed more than about twenty tools.

Each entry links to its full input/output schema, pricing and worked examples.

Contamination & environmental due diligence (19)

environmental-records-report · epa-airtoxscreen-cancer-risk-screener · epa-contaminated-site-screener · epa-drinking-water-quality-screener · epa-ghgrp-emitter-screener · epa-impaired-waters-303d-screener · epa-nonattainment-air-permit-screener · epa-rcra-corrective-action-cleanup-monitor · epa-rcra-hazwaste-generator-rollup · epa-repowering-brownfield-to-solar-site-finder · epa-sole-source-aquifer-screener · epa-tri-facility-release-rollup · epa-tsca-cdr-chemical-site-screener · erns-nrc-release-incident-screener · fuds-defense-site-screener · historic-land-use-sic-contaminant-screener · site-due-diligence-bundle · state-tank-spill-registry-screener · usgs-historical-topo-records-review

Flood, fire, quake & ground hazard (13)

calfire-fhsz-screener · cbrs-coastal-barrier-screener · fema-nri-county-risk-profile · fema-repetitive-loss-flood-market-screener · karst-sinkhole-risk-screener · nfip-flood-loss-risk-screener · noaa-slr-inundation-threshold-screener · noaa-storm-events-peril-climatology · usace-levee-flood-risk-screener · usgs-bedrock-geology-lithology-screener · usgs-landslide-proximity-screener · usgs-seismic-design-screener · wildfire-asset-exposure-screener

Habitat, wetlands, protected & historic land (9)

blm-sage-grouse-siting-screener · fws-critical-habitat-screener · fws-wetlands-proximity-screener · nhd-surface-water-404-screener · noaa-efh-consultation-screener · nrhp-historic-place-screener · padus-protected-lands-screener · tribal-land-jurisdiction-screener · wild-scenic-river-proximity-screener

Energy siting, grid & pipelines (14)

blm-mining-claims · blm-solar-siting-area-screener · boem-offshore-wind-lease-tracker · cdfi-nmtc-lowincome-energy-bonus-screener · eia-v2-site-energy-economics · energy-corridor-368-screener · hifld-grid-proximity-screener · interconnection-queue-tracker · ira-energy-community-bonus-screener · nrel-pvwatts-solar-resource-scorer · ntad-gas-pipeline-proximity-screener · oil-gas-well-permits · orphaned-well-proximity-screener · uswtdb-turbine-proximity-screener

Farmland, soil & water (5)

ssurgo-soil-suitability-screener · usda-cdl-farmland-siting-screener · usgs-groundwater-depth-screener · usgs-nwis-streamflow-monitor · water-rights-availability-screener

Banking, lending & credit (9)

bank-enforcement-tracker · fdic-branch-network-churn-rollup · fdic-ncua-health-rollup · fdic-sod-deposit-market-share-rollup · fdic-structure-change-delta-monitor · fhlbank-membership-delta-monitor · hmda-fair-lending-disparity-rollup · sba-loan-portfolio-explorer · ucc-lapse-refinance-window

Securities, audit, pensions & sanctions (10)

adcvd-trade-remedy-tracker · consolidated-screening-list-delta · fec-campaign-finance-delta · pbgc-pension-failure-monitor · pcaob-auditor-engagement-monitor · reg-a-plus-lifecycle-monitor · reg-cf-lifecycle-monitor · ria-registration-delta-monitor · short-interest-ftd-monitor · uflpa-entity-list-monitor

Licensing, exclusion & workforce screening (10)

city-business-license-leads · gleif-ownership-graph · hrsa-clinician-workforce-monitor · hrsa-shortage-designation-monitor · kyb-company-verifier · license-verifier · liquor-license-new-openings-tracker · medicaid-exclusion-screener · realtor-license-roster-delta · sos-registry-monitor

Real estate, parcels, deeds & leads (9)

absentee-owner-lead-list-builder · acris-deed-transfer-intel · childcare-provider-leads · distressed-property-signal-stacker · hud-affordable-housing-explorer · hud-qct-lihtc-boost-screener · hud-section8-contract-expiration-monitor · nyc-landlord-registry-lead-list · parcel-owner-lookup

Infrastructure, transport & airspace (10)

bts-airline-ontime-delay-climatology · bts-db1b-fare-route-market-analytics · dod-mirta-military-installation-siting-screener · faa-drone-airspace-checker · fhwa-nbi-bridge-risk-monitor · gsa-site-scanning-auditor · national-tunnel-inventory-risk-monitor · nhtsa-vpic-vin-decoder · nid-dam-risk-monitor · ntad-fra-rail-crossing-risk-screener

Health, clinical & drug supply (7)

cdc-nndss-outbreak-monitor · clinical-trials-meta-search · cms-open-payments · cms-part-d-prescriber-delta · drug-shortage-delta-monitor · nadac-price-movers · usmin-mine-feature-proximity-screener

Patents, IP & company data (5)

ca-data-broker-registry-delta · npm-package-health-scorer · ptab-trial-tracker · sbom-vulnerability-rollup · uspto-patent-lapse-fto-monitor

Labor & enforcement (3)

dol-enforcement-rollup · osha-ita-injury-illness-establishment-monitor · warn-layoff-aggregator

Development

npm install
npm test              # offline suite, no network
node tools/mutate.cjs # re-injects known defects, asserts the suite catches them
npm run catalog -- <apify-token>   # regenerate src/catalog.json from the live API

License

MIT