# US Government Data (npm · gov-data-mcp)

US government open-data APIs as MCP tools: EPA, FEMA, USGS, NOAA, FDIC, HUD, CMS and more.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-21

## Components

- npm · `gov-data-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/malonestar-gov-data-mcp/gov-data-mcp.md), [page](https://verifymcp.io/servers/malonestar-gov-data-mcp/gov-data-mcp)

## Channel facts

- Registry: `npm`
- Package: `gov-data-mcp`
- Version: `1.0.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-21.

- **Supply Chain Security**: 48/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to malonestar/gov-data-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 10004 tokens (~666/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add malonestar-gov-data-mcp -- npx -y gov-data-mcp
```

### Codex

```bash
codex mcp add malonestar-gov-data-mcp -- npx -y gov-data-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "malonestar-gov-data-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "gov-data-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add malonestar-gov-data-mcp --command npx --arg -y --arg gov-data-mcp
```

### Hermes

```yaml
mcp_servers:
  malonestar-gov-data-mcp:
    command: "npx"
    args: ["-y", "gov-data-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "malonestar-gov-data-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "gov-data-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-21 (score 61, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 1.0.2 → 1.0.3

### 2026-08-20 (score 60)

First indexed and scored.

## MCP tools (15)

### `site-due-diligence-bundle` (~458 tokens)

Environmental Due Diligence Bundle: 20-Layer Site Scorecard. Environmental due diligence in one call: lat/lon plus radius returns a go/caution/no-go fatal-flaw verdict and a 0-100 site score across 20 federal layers - EPA contamination, FEMA flood, NWI wetlands, ESA habitat, NAAQS nonattainment, NRHP historic, karst, landslide, levee, dams, CBRS, pipelines. Reads live from the official government source. Store page: https://apify.com/malonestar/site-due-diligence-bundle

Input parameters:

- `assets` (array, required): List of sites to run the full fatal-flaw scorecard on. Each item is an object with numeric lat and lon (WGS84 decimal degrees) and an optional label. One billable scorecard row is returned per succes…
- `maxAssets` (integer): Maximum number of assets to screen from the list (safety cap). Extra assets beyond this are ignored. Applied by default if omitted: 250.
- `radiusMiles` (number): Search radius in statute miles for the proximity layers (EPA contamination, ESA critical habitat, transmission grid, wildfire flag, landslide nearby-search, CWA 303(d) impaired waters, tank/spill reg…

### `epa-contaminated-site-screener` (~1614 tokens)

Phase I ESA & Environmental Due Diligence: EPA Database Search. Environmental due diligence by address: an environmental database report over EPA Superfund/NPL, RCRA CORRACTS/TSD/generators, TRI, UST, LUST, Brownfields, NPDES, AIR, TSCA and RMP, scored at ASTM E1527-21 search distances, plus on-site Superfund and AUL boundary checks. No API key. Reads live from the official government source. Store page: https://apify.com/malonestar/epa-contaminated-site-screener

Input parameters:

- `assets` (array): Locations to screen against EPA contaminated-site databases. Each item is EITHER {"address": "...", "label": "..."} (geocoded via the free Census geocoder) OR {"lat": <number>, "lon": <number>, "labe…
- `astmMode` (boolean): Assets mode only. Adds ONE extra "astm_summary" row after each asset's normal rows, scoring this actor's databases against the ASTM E1527-21 Sec. 8.2.1 standard search distances. The refined table sp…
- `includeBoundaries` (boolean): Assets mode only. Runs two extra point-in-polygon queries per asset to answer "is this property ON a Superfund site?" (on_superfund_site, superfund_site_name, superfund_epa_url) and "is it inside a p…
- `maxHitsPerProgram` (integer): Assets mode only: cap on the number of nearest site hits reported per program per asset (keeps output and billing bounded near dense industrial areas). The nearest sites are kept. Default 50. Range 1…
- `maxResults` (integer): Safety cap on total dataset rows produced across the run: max site hits emitted (assets mode) or max SEMS site rows (inventory mode). Applied by default if omitted: 1000.
- `mode` (string): "assets" (default) runs a multi-database Phase I ESA-style regulatory-records screen on your addresses/coordinates — one billable row per nearby EPA-listed site (across Superfund, RCRA, TRI, UST, LUS…
- `onlyNpl` (boolean): Inventory mode only: when true, keep only sites currently on (or part of) the National Priorities List — the actual Superfund program sites. When false, include all SEMS site statuses. Default false.…
- `onlyWithCoords` (boolean): Inventory mode only: when true (default), drop SEMS records with no latitude/longitude. Coordinate coverage varies sharply by state — measured 2026-07: 3% of Texas SEMS records carry coordinates, 16%…
- `programs` (array): Which EPA program databases to include. The six defaults: SUPERFUND (NPL/SEMS), RCRA (hazardous-waste handlers, now classified into CORRACTS / TSD / generator), TRI (Toxics Release Inventory), UST (u…
- `radiusMiles` (number): Distance from each asset within which EPA-listed sites are counted and reported across all selected programs. Accepts fractional miles (0.1-50) so you can screen at the ASTM E1527-21 standard search…
- `states` (array): 2-letter US state codes (e.g. ["CO", "NJ"]) whose EPA SEMS/Superfund site records to list. Required when Mode = inventory. Ignored in assets mode (state is derived automatically per-asset).
- `strictDataCompleteness` (boolean): Assets mode only. Reserved for callers that must not accept partial coverage. Regardless of this setting, every row already carries programs_screened / programs_failed / data_complete, and an asset w…

### `faa-drone-airspace-checker` (~631 tokens)

FAA Drone Airspace Checker - Batch LAANC & No-Fly Verdicts. Batch lat/lon to FAA UAS airspace verdicts: LAANC ceilings AND whether LAANC is actually offered, charted Class B/C/D/E surface areas, prohibited areas, national-defense TFR areas, special use airspace, NSUFR, stadium TFRs. Verdict is gated - it never reads clear when a layer did not answer. Reads live from the official government source. Store page: https://apify.com/malonestar/faa-drone-airspace-checker

Input parameters:

- `layers` (array): Which FAA airspace layers to check each point against. Defaults to all eight. laanc_grid = UAS Facility Map LAANC ceilings; class_airspace = charted Class A/B/C/D/E airspace (ALWAYS queried - it is t…
- `maxPoints` (integer): Safety cap on the number of points checked (and billed) in one run. Points beyond the cap are skipped with a warning. Applied by default if omitted: 500.
- `points` (array, required): Locations to check, in WGS84 decimal degrees. Each item is either an object like {"lat": 39.86, "lon": -104.67, "label": "Site A"} (label optional; latitude/longitude aliases accepted) or a "lat,lon"…

### `hifld-grid-proximity-screener` (~1200 tokens)

Transmission Line & Substation Distance API by Coordinates. For each lat/lon site: distance to the nearest transmission line (kV, owner, overhead/underground), nearest substation, nearest power plant, the serving utility and its ISO/RTO, plus generation and battery-storage MW nearby. Includes sub-100 kV. Data-center, renewable, BESS and EV siting. Reads live from the official government source. Store page: https://apify.com/malonestar/hifld-grid-proximity-screener

Input parameters:

- `allowTruncatedLineFallback` (boolean): The transmission-line answer comes from a national layer of 94,619 lines. If that layer is unavailable, the only backup is a 2023 copy that contains NO line below 100 kV — 44.8% of the US grid, and t…
- `assets` (array, required): Sites to screen for grid access. Each entry is an object { "lat": number, "lon": number, "label": "optional name" }. Also accepts "lat,lon" strings or [lat, lon] arrays. One dataset row (one billed r…
- `eiaApiKey` (string): Optional. A free EIA API key (https://www.eia.gov/opendata/register.php) enables the state industrial and commercial electricity price columns. Everything else works without it — leave this empty and…
- `includePlanned` (boolean): Advanced/opt-in. Also check a 'planned transmission line' scratch layer that carries NO owner/voltage/status metadata. It is NOT an authoritative planned-line dataset — the planned_line_nearby flag i…
- `includePowerPlants` (boolean): Also report the nearest power plant (name, distance, fuel, technology, capacity MW, EIA plant code) plus total generation, battery-storage, solar and wind MW within the radius. Sourced from EIA's mon…
- `includeSubstations` (boolean): Also report the nearest electric substation (name, distance, max/min voltage, connected line count) plus substations within the radius. On by default — set to false to skip substation screening and s…
- `includeUtility` (boolean): Also resolve which retail electric utility serves each site, its ownership type, holding company, customer count and summer peak, plus the balancing authority and ISO/RTO (PJM, ERCOT, CAISO, MISO, SP…
- `maxResults` (integer): Maximum number of assets processed in one run (1-2000). One result row is emitted (and billed) per asset. Default 500. Applied by default if omitted: 500.
- `minVoltageKv` (integer): Optional. Only count/consider transmission lines at or above this many kV. Since v1.2 the underlying layer includes sub-100 kV sub-transmission (69/46/34.5 kV), so values below 100 are now meaningful…
- `radiusMiles` (integer): Radius around each asset to search for transmission lines, substations and power plants, in miles (1-50). Features beyond this distance are ignored. Default 5. Example: 10. Applied by default if omit…
- `simulateOutage` (string): Diagnostic seam for verifying the reliability behaviour on demand rather than waiting for a real outage. "none" (default) is a genuine no-op. "primary" forces the primary line layer to appear down; "…
- `skipErrorRows` (boolean): When true, assets that could not be screened are logged but not written to the dataset, so you are not billed for them. Default false, which keeps every asset accounted for as an ERROR row. Note that…

### `interconnection-queue-tracker` (~641 tokens)

US Interconnection Queue Tracker - 7 ISO Queues & Deltas API. Normalize US ISO/RTO generator interconnection queues (SPP, MISO, NYISO, CAISO, PJM, ERCOT, ISO-NE) into one schema and track new, withdrawn, status-change and COD-slip deltas. For renewables developers, land agents, and energy consultants. Keyless. Reads live from the official government source. Store page: https://apify.com/malonestar/interconnection-queue-tracker

Input parameters:

- `deltaOnly` (boolean): Snapshot mode only. When true, suppress unchanged queue rows and emit ONLY new/status-changed rows, synthetic withdrawn rows, and one iso_summary roll-up row per ISO — ideal for a scheduled weekly/da…
- `isos` (array): ISO/RTO codes to pull. Leave empty to pull ALL 7 live sources (SPP, MISO, NYISO, CAISO, PJM, ERCOT, ISO-NE) in one run. All 7 are keyless - no account or API key needed. An unrecognised code now FAIL…
- `maxResults` (integer): Maximum number of queue records to fetch across ALL selected ISOs combined. The cap is applied in ISO order, so a low value truncates the last ISOs: any ISO that is cut short or never reached is mark…
- `mode` (string): snapshot = emit the current normalized queue, automatically annotated with monitor fields (is_new_since_last_run, status_changed, previous_status) vs. the actor's own self-managed KV snapshot, plus s…
- `priorItems` (array): Delta mode: the prior run's unified queue items (the array of records this actor produced before). The diff is computed purely against these. Ignored in snapshot mode. Applied by default if omitted:…
- `priorKvKey` (string): Delta mode alternative to priorItems: a key in this actor's key-value store holding the prior snapshot. When set, the current snapshot is also SAVED under this key so scheduled runs diff automaticall…

### `fdic-ncua-health-rollup` (~1060 tokens)

Bank & Credit-Union Financial Health API — FDIC/NCUA QoQ. Bank & credit-union financial-health API on keyless FDIC data (NCUA v1.1): unified per-institution assets, deposits, equity, ROA, ROE, NIM and asset quality, with quarter-over-quarter deltas, peer-percentile scoring, and derived health flags (deposit outflow, low ROA, rising NPL). Reads live from the official government source. Store page: https://apify.com/malonestar/fdic-ncua-health-rollup

Input parameters:

- `benchmark` (string): Adds asset-weighted benchmark ratios and this bank's distance from them, in percentage points: benchmark_uninsured_deposit_ratio, benchmark_cre_to_tier1_pct, benchmark_unrealized_loss_to_equity_pct p…
- `creGrowth` (boolean): The 2006 interagency CRE guidance is TWO tests: construction >= 100% of capital, OR (CRE >= 300% of capital AND CRE grew >= 50% over 36 months). Leaving this on fetches the quarter from 12 quarters a…
- `institutionType` (string): Which institutions to include. 'bank' = FDIC-insured banks, fully supported, the only option that returns data today. 'credit_union' = NCUA — NOT AVAILABLE YET (ships in v1.3); selecting it alone fai…
- `maxAssets` (integer): Only include institutions with at most this many total assets, in thousands of dollars. 0 = no ceiling. Combine with minAssets to score within an asset-size peer band (e.g. community banks $250M–$1B)…
- `maxResults` (integer): Maximum number of institution-health records to return after filtering, scoring, and ranking. This is your cost cap: one record = one billable result. 500 covers a full mid-size state; TX has ~380 ba…
- `minAssets` (integer): Only include institutions with at least this many total assets, in thousands of dollars (FDIC reports assets in $000s, so 1000000 = $1B). Use with maxAssets to build a peer band. 0 = no floor. Applie…
- `mode` (string): Every mode returns the SAME full field set — capital ratios, uninsured deposits, unrealized losses, CRE concentration, credit quality and quarter-over-quarter deltas. Mode changes the ordering only.…
- `peerBasis` (string): What counts as a 'peer' when computing peer_asset_percentile, peer_roa_percentile, peer_cre_percentile and peer_uninsured_percentile. 'cohort' scores against everything you pulled (a state cohort mix…
- `priorItems` (array): Optional. In delta mode, an array of institution rows from a previous run (each needs id, total_assets, total_deposits) to diff the current quarter against, instead of auto-fetching the prior quarter…
- `state` (string): US state to scope the cohort, e.g. CA, TX, NY. Strongly recommended: it focuses the run and makes peer percentiles state-level. Empty = the entire country (slower; national peer scoring). Example: "T…

### `fema-nri-county-risk-profile` (~554 tokens)

FEMA NRI County Risk Profile — Asset Hazard Join. Join any asset (address, lat/lon, or county FIPS) to FEMA's National Risk Index hazard profile at county or census-tract resolution: composite risk score, expected annual loss, social vulnerability, resilience, and ranked top-3 hazards across all 18 FEMA perils. Reads live from the official government source. Store page: https://apify.com/malonestar/fema-nri-county-risk-profile

Input parameters:

- `assets` (array): Locations to profile. Each item is EITHER {fips:"08031"} (5-digit county FIPS), OR {state:"Colorado", county:"Denver"}, OR {lat:39.7392, lon:-104.9903} (geocoded via the keyless FCC Census Block API)…
- `counties` (array): Used only when Assets is empty. Narrows the States filter above to specific bare county names (no "County"/"Parish" suffix), e.g. Denver. Applies at both county and tract resolution.
- `maxResults` (integer): Maximum number of output records (each is one billed result). In asset mode this caps the number of assets processed; in inventory mode it bounds the row count returned (there are ~3,144 US counties…
- `resolution` (string): Geographic resolution to join against: "county" (default — ~3,144 US counties) or "tract" (~85,000 US census tracts, finer-grained). Tract resolution only applies to lat/lon assets (geocoded to a tra…
- `states` (array): Used only when Assets is empty. Return full NRI risk profiles for these US states (2-letter postal codes or full names, e.g. CO or Colorado) at the resolution set above (county or tract). Leave empty…

### `fws-wetlands-proximity-screener` (~617 tokens)

USFWS Wetlands Proximity Screener - Section 404 Site Risk API. Wetland due-diligence API for site selection: per lat/lon site, wetland presence within radius, Cowardin classification codes/systems, wetland types, total acreage nearby and a Section 404 dredge-and-fill screening flag. USFWS National Wetlands Inventory open data. Reads live from the official government source. Store page: https://apify.com/malonestar/fws-wetlands-proximity-screener

Input parameters:

- `assets` (array, required): Sites to screen for wetlands. Each entry is an object { "lat": number, "lon": number, "label": "optional name" }. Also accepts "lat,lon" strings or [lat, lon] arrays. One dataset row (one billed resu…
- `computeNearestDistance` (boolean): When on (default), the actor measures the true distance and bearing to the nearest NWI wetland polygon instead of reporting a largest-acreage proxy. Costs up to ~10 small extra requests per site. Tur…
- `maxResults` (integer): Maximum number of assets processed in one run (1-2000). One result row is emitted (and billed) per asset. Default 500. Applied by default if omitted: 500.
- `nearestSearchRadiusMeters` (integer): How far out to look for the nearest wetland, in meters (up to 8000). Independent of the screening radius, so a site can correctly read 'no wetland within 300 m' and still report the closest one 1,391…
- `radiusMeters` (integer): Radius around each asset used for the wetland-presence check, in meters (10-5000). Screened as a TRUE circle. Default 300 (~984 ft, roughly a parcel-scale buffer). Example: 300.

### `nhd-surface-water-404-screener` (~748 tokens)

NHD Surface Water & Section 404 Wetland Screener. Screen any lat/lon against USGS NHDPlus HR surface water. 94 fields: exact distance to the nearest perennial, intermittent and ephemeral reach, waterbody type and purpose, mean annual flow, stream order, HUC-8/10/12, a jurisdictional-likelihood call with its reasoning, and a Section 404/WOTUS flag. Reads live from the official government source. Store page: https://apify.com/malonestar/nhd-surface-water-404-screener

Input parameters:

- `assets` (array, required): Required. The list of sites to screen, in the standard [{lat, lon, label}] shape. Use decimal degrees (lon is negative in the USA). label is optional free text - it is echoed on every output row so y…
- `includeNonNetworkFlowlines` (boolean): Also query NHDPlus HR layer 4 (NonNetworkNHDFlowline) for isolated ditches, canals and disconnected reaches near the site. Leave on for a conservative wetland-delineation scope; turn off to save one…
- `maxResults` (integer): Upper bound on the number of assets screened, and therefore on the number of dataset rows produced. One asset always produces exactly one row, including sites that turn out to be far from any mapped…
- `radiusMeters` (integer): How far around each site to look for NHD flowlines, waterbodies and water areas. 1000 m covers a typical Phase-I ESA adjacent-property review; widen to 3000 m for utility-scale solar, BESS or data-ce…

### `epa-drinking-water-quality-screener` (~811 tokens)

EPA Drinking Water Quality Screener - Violations, Lead & PFAS. Screen any US coordinate for the public water system serving it: SDWA health-based violations, Lead & Copper Rule 90th-percentile results and UCMR5 PFAS detections - the evidence base behind the LCRI (Nov 1, 2027) and PFAS NPDWR (Apr 26, 2027) deadlines. Never clears a source that did not answer. Reads live from the official government source. Store page: https://apify.com/malonestar/epa-drinking-water-quality-screener

Input parameters:

- `assets` (array): Sites to screen, each {"lat": <number>, "lon": <number>, "label": "<your name for the site>"}. Each location is matched against EPA's mapped community water system service areas to identify the servi…
- `includeEnforcement` (boolean): Fetch the system's SDWIS formal enforcement action history and report the count and most recent action. Example: true.
- `includeLead` (boolean): Fetch Lead and Copper Rule 90th-percentile tap results and join them to their monitoring periods, so the reported value is dated rather than undated. Example: true.
- `includePfas` (boolean): Screen the system against EPA's UCMR5 occurrence dataset (1.9 million results, 29 PFAS analytes plus lithium). Turn off for a faster run when PFAS is out of scope. Example: true.
- `includeViolations` (boolean): Fetch the system's full Safe Drinking Water Act violation history from EPA SDWIS and roll it up (health-based, monitoring/reporting, treatment technique, Lead & Copper Rule, public-notification tier)…
- `maxAssets` (integer): Safety cap on how many locations are screened in one run. Locations beyond the cap are reported in the log and not billed. Example: 250.
- `maxViolationDetails` (integer): How many individual health-based violation records to include in the health_based_violation_details array on each row, newest first. Counts are never truncated. Example: 25.
- `pwsids` (array): Optional. Screen specific public water systems by 9-character EPA PWSID (for example ["MI0002310"]) without a coordinate lookup. Combined with any locations supplied above. Example: [].
- `refreshPfasCache` (boolean): Re-download and re-index the UCMR5 occurrence file even if the cached index already matches EPA's current published vintage. Normally unnecessary: the cache is keyed to the file's Last-Modified heade…
- `runBudgetSeconds` (integer): Total time budget for all upstream requests including retries. Requests stop rather than retry past this budget, so a long EPA outage fails loudly instead of hanging. Example: 900.
- `simulateOutage` (string): Diagnostic seam for verifying failure behaviour. Forces one or all EPA sources to fail so you can confirm the actor reports the source as unavailable and never publishes a false clear. Leave as none…
- `violationYears` (integer): How many years back counts as a recent health-based violation for the screening flags. The full violation history is still summarised regardless. Set 0 to disable the window. Example: 10.

### `parcel-owner-lookup` (~276 tokens)

Parcel Owner Lookup — Address to Owner & Assessor Record. Turn street addresses into parcel IDs, owner names, mailing addresses, assessed values & coordinates from official assessor rolls (Chicago/Cook County, Philadelphia, NYC) with Census-geocoder fallback. Address-grounding primitive for AI agents, proptech & skip tracing. $0.02/lookup. Reads live from the official government source. Store page: https://apify.com/malonestar/parcel-owner-lookup

Input parameters:

- `addresses` (array, required): US street addresses to resolve to a parcel + owner record, one per line (e.g. '1060 W Addison St, Chicago, IL'). v1 matches against the Cook County IL (Chicago), Philadelphia PA, and New York City as…
- `maxResults` (integer): Maximum number of addresses to process (one output row per address). Extra addresses beyond this cap are skipped. Example: 10. Applied by default if omitted: 100.

### `license-verifier` (~1103 tokens)

License Verification API — Nurses, MDs & OIG Exclusions. Primary source verification for US professional licenses. Search 19 state boards by name or license number: status, expiration, disciplinary actions. Cross-checks the NPPES NPI registry and screens the HHS-OIG exclusion list. Bulk roster screening. Reads live from the official government source. Store page: https://apify.com/malonestar/license-verifier

Input parameters:

- `businessName` (string): Business or DBA name to search (partial match).
- `checkDiscipline` (boolean): Join the best-matching licensee against secondary board-action datasets: Delaware DPR disciplinary actions and the NYS Office of Professional Medical Conduct. A failed lookup is reported as unknown,…
- `city` (string): City to filter licensees by. Not every board publishes a city column.
- `firstName` (string): Licensee first name (partial match). Supplying it raises match confidence sharply — first + last name exact is the threshold for a confident verdict. Example: "Judson". Applied by default if omitted:…
- `lastName` (string): Licensee last name (partial match). Example: "Threlkeld". Applied by default if omitted: "".
- `licenseNumber` (string): Exact license number to verify. The most precise search available — use it when you have it.
- `licenseType` (string): e.g. "Registered Nurse", "Real Estate", "Cosmetology", "Professional Engineer". Boards without a license-type column skip this filter and say so in the log and in unsupported_filters.
- `maxResults` (integer): Maximum number of license records to return per board. Each returned row is billable, so start small. Example: 10. Applied by default if omitted: 200.
- `name` (string): Full-name search that works across every board (handles combined name fields). Use this if lastName/firstName return nothing.
- `npiLookup` (boolean): For each roster entry, look the person up in the federal NPI registry and use their self-reported state license number to pin down the exact board record. This is what turns 125 same-name candidates…
- `onlyDisciplined` (boolean): Return only licensees with a disciplinary history. Honoured by IL-IDFPR, CO-DORA, DE-DPR, WA-DOH, TX-BON and TX-LVN. Target those board IDs directly rather than a bare state code, or sibling boards t…
- `roster` (array): Batch mode: verify a whole roster of professionals in one run. Each item: {firstName, lastName, state (optional — omit to search every board), profession (optional), middleName (optional, improves sc…
- `rosterLimitPerBoard` (integer): How many candidate records to pull per board for each roster entry before scoring. Higher values reduce the chance of missing the right person for a common surname; candidates_truncated tells you whe…
- `screenExclusions` (boolean): Check every result against the federal HHS-OIG List of Excluded Individuals/Entities (83,000+ records, refreshed monthly). Matched on NPI first, then last+first+state. A surname-only hit is NEVER rep…
- `socrataAppToken` (string): Optional free Socrata app token to raise rate limits.
- `states` (array): State codes or explicit board IDs. A bare state code searches EVERY board in that state - e.g. "TX" covers TDLR trades AND the Board of Nursing (RN, LVN, APRN). Use a hyphenated ID to target ONE boar…
- `statusOnly` (boolean): Return only license number, type, status, expiration, provenance and the OIG exclusion flags. Handy for recurring renewal monitoring. NOTE: this is the SAME price per row as a full record — it return…

### `search_gov_data_tools` (~115 tokens)

Search the full catalog of 114 US government data tools by keyword, agency, or topic (e.g. "wetlands", "FDIC", "flood", "drone airspace", "business licenses"). Returns matching tool names with descriptions. Use this first when the task is not covered by one of the dedicated tools above.

Input parameters:

- `limit` (integer): Maximum number of results to return. Default 10.
- `query` (string, required): Keywords to match against tool name, title, description and category.

### `describe_gov_data_tool` (~72 tokens)

Return the full input schema and documentation for any one of the 114 tools in the catalog. Call this before run_gov_data_tool so the input is correctly shaped.

Input parameters:

- `tool` (string, required): The tool name, e.g. "noaa-slr-inundation-threshold-screener".

### `run_gov_data_tool` (~104 tokens)

Run any one of the 114 catalog tools with the given input and return its rows. Billed to your own Apify account at the tool's published rate.

Input parameters:

- `input` (object, required): Input object matching the schema returned by describe_gov_data_tool.
- `maxItems` (integer): Maximum rows to return. Default 200.
- `tool` (string, required): The tool name to run, e.g. "usgs-seismic-design-screener".

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/malonestar-gov-data-mcp/gov-data-mcp#diagnostics

## Score history

- 2026-08-21: 61
- 2026-08-20: 60

## Links

- npm package: https://www.npmjs.com/package/gov-data-mcp
- Socket report: https://socket.dev/npm/package/gov-data-mcp
- Repository: https://github.com/malonestar/gov-data-mcp
- Website: https://apify.com/malonestar
- Changelog RSS feed: https://verifymcp.io/servers/malonestar-gov-data-mcp/gov-data-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/malonestar-gov-data-mcp/gov-data-mcp.json
- HTML version of this page: https://verifymcp.io/servers/malonestar-gov-data-mcp/gov-data-mcp