Skip to content
FonteumThe Graph

The capability layer

APIREST + bulk accessMCP serverCallable by AI agentsFHIR R4 APIBulk exportAttestation & audit packReconciliationSource-vs-source diffsEntity graphSnapshotsPoint-in-time, bitemporal

By use case

Exclusion & sanctions screeningCredentialing & provider-data enrichmentAudit evidence & defensible programsProvider data for AI / RAGM&A & network diligence

By buyer

Compliance & riskDevelopers & AI teams

The differentiator

Coverage & sourcesThe catalogFreshnessMethodologyCare CompareFacility qualityBrowse all datasets →
Research

The dev on-ramp

DocsAPI referenceMCPQuickstartStatusChangelogSDKs & integrations
Pricing
Sign inTry the FHIR sandbox →Request access →

Platform

APIMCP serverFHIR R4 APIBulk exportAttestation & audit packReconciliationEntity graphSnapshots

Solutions

Exclusion & sanctions screeningCredentialing & provider-data enrichmentAudit evidence & defensible programsProvider data for AI / RAGM&A & network diligenceCompliance & riskDevelopers & AI teams

Data

Coverage & sourcesFreshnessMethodologyCare CompareBrowse all datasets →
Research

Developers

DocsAPI referenceMCPQuickstartStatusChangelogSDKs & integrations
Pricing
Sign inTry the FHIR sandbox →Request access →

DEVELOPERS · THE ON-RAMP

Build on federal healthcare data in an afternoon.

A REST API, an MCP server for agents, HL7 FHIR R4, SDKs, and a screening CLI — all over one source-provenanced US healthcare provider graph drawn from 44 federal source families. Sandbox key, no contract to start, provenance on every field.

Start the quickstartRead the docs →

The surfaces

Pick your integration path

REST

API

Resolve a provider across NPPES, OIG LEIE, CMS PECOS, Care Compare, and Open Payments in one GET — every field carrying its 14-tuple provenance.

Open API→
Reference

API reference

Endpoint-by-endpoint reference for the /api/v1 surface: auth, rate limits, the freshness contract, and the response envelope.

Open API reference→
Agents

MCP server

A Model Context Protocol server an AI agent calls directly — resolve, screen, and pull provenance with no human in the loop.

Open MCP server→
Interop

FHIR R4 API

HL7 FHIR R4 US Core 6.1.0: Practitioner, Organization, Location, PractitionerRole, HealthcareService, with SMART Backend Services auth and Bulk $export.

Open FHIR R4 API→
SDKs

SDKs & integrations

A Python SDK, an npm package, and framework adapters — plus the screening CLI and GitHub Action that fail a build when a tracked NPI is excluded.

Open SDKs & integrations→
Egress

Bulk export

Whole-dataset downloads as gz-compressed NDJSON and CSV across every ingested federal source family, discoverable through one manifest.

Open Bulk export→
Events

Webhooks

Subscribe to provenance-stamped provider events. HMAC-SHA256-signed POSTs fire when LEIE or PECOS state changes for a tracked provider.

Open Webhooks→
Start here

Quickstart

The fastest path in: a sandbox key, a first FHIR read, and a sample dataset download — no contract to begin.

Open Quickstart→

Reference & operations

Docs, status, and changelog

Docs

Documentation home

Every guide, reference, and spec in one index.

Status

Status

Live availability and incident history.

Changelog

Changelog

Dated, one-line entries for every shipped change.

Developer FAQ

Common questions

What developer surfaces does Fonteum offer?
Four ways in: a REST API for direct queries, an MCP server for AI agents, an HL7 FHIR R4 interface for clinical interoperability, and bulk export for whole-dataset downloads. SDKs, a screening CLI, and a GitHub Action wrap those surfaces for common workflows.
Do I need to authenticate to start?
Anonymous reads of individual resources are permitted and rate-limited. A free sandbox key raises limits; SMART Backend Services authentication is required for FHIR Bulk $export. There is no contract to begin building.
What federal data powers the developer APIs?
The APIs draw from 44 federal source families including NPPES, CMS PECOS, OIG LEIE, CMS Care Compare, HCRIS, QPP MIPS, and HRSA. Every field carries a 14-tuple provenance chain tracing back to the originating federal record.
How does the screening CLI and GitHub Action work?
The CLI screens a list of NPIs against the exclusion lists and exits non-zero on a match; the GitHub Action runs it in CI so a workforce or vendor change that introduces an excluded provider fails the build. Both return the matching list, the exclusion date, and the source citation.
Is freshness exposed in the API?
Yes. Freshness is a first-class field: every response carries the snapshot date and last-checked timestamp for each source, and a behind-SLA source is a flag in the payload, not a silent gap. A caller can set a max-staleness policy and have the API fail closed.
Can I get the data in bulk instead of per request?
Yes. Bulk export ships gz-compressed NDJSON and CSV for every ingested source family, indexed by a machine-readable manifest so a harvester discovers all families through one URL. FHIR Bulk $export streams the provider dataset as NDJSON.

Go deeper

Where to go next

  • PlatformThe capability layer behind the APIs
  • SolutionsWhat teams build with the APIs
  • DataCoverage, sources, and the data catalog
  • ResearchOriginal studies built on the graph
START BUILDING

Call the API or drop the MCP server into your agent.

Grab a sandbox key, make a first FHIR read, or screen an NPI from the CLI. Provenance rides on every field — no contract to begin.

Add Fonteum to your agent →Request pilot access

Built on the authoritative federal record

The primary sources, named on every page.

These are the federal agencies whose public datasets Fonteum ingests and attributes — the issuing authorities, not customers or partners. Every figure on the site links back to one of them.

  • CMS
  • HHS-OIG
  • HRSA
  • FDA
  • NLM
  • NUCC
  • Census
  • BLS
  • BEA

See the full source registry, with license and refresh cadence for each →

Reproducible by design

Every figure traces to its federal source.

14-tuple provenance

Every rendered fact ties to a source URL, dataset ID, snapshot date, row key, and SHA-256 — the full chain-of-custody record.

Reproducible SQL

Each study ships the exact query behind its figures, run against the cited federal snapshot. Re-run it yourself.

Daily reconciliation

Published counts are reconciled against the upstream federal datasets on a daily cadence, with drift logged.

Named medical review

Reviewed by Jennifer Montecillo, MD, medical reviewer. Non-practicing medical reviewer.

Read the full provenance and attestation methodology →

Two doors

Use the free API and open data

Query providers, facilities, sanctions, and quality scores — each field carrying its federal source. Self-serve, no call to start.

Explore the API →Browse the data catalog →

Talk to us

Managed pilots, enterprise terms, and audit-ready, signed attestation packages for compliance, risk, and research teams.

Talk to us →
Fonteum
Platform
Platform overviewAPIMCP serverFHIR R4 APIBulk exportAttestation & audit packReconciliationEntity graphSnapshots
Solutions
All solutionsExclusion & sanctions screeningCredentialing & enrichmentAudit evidenceProvider data for AI / RAGM&A & network diligenceCompliance & riskDevelopers & AI teams
Data & sources
Coverage & sourcesBrowse all datasetsFreshnessMethodologyCare CompareSanctionsOwnershipStaffingDeficienciesSpecial Focus Facilities
Developers
Developer hubDocsAPI referenceQuickstartStatusChangelogSDKs & integrationsWebhooks
Research
Research hubGlossaryComparisonsCitationsWhy Fonteum
Company
AboutPressCustomersPricingContactEditorial policyCorrections
Trust & legal
TrustQualitySecurityPrivacy policyTerms of serviceMedical disclaimer

Reviewed by Jennifer Montecillo, MD, medical reviewer. Non-practicing medical reviewer.

© 2026 Fonteum LLC. All rights reserved.

The U.S. healthcare graph AI can cite — every fact carries its source.

Request access→

The substrate, by the numbers

9.2Mgraph entitiesProviders, organizations, owners, and facilities
15.7Mlinked identifiersNPIs, CCNs, LEIs and more, resolved to entities
5Mgraph edgesSource-attested relationships between entities
44federal source familiesDistinct CMS, OIG, HRSA, FDA and peer datasets
35dataset pagesCitable, downloadable /data catalog pages
65reproducible studiesEach shipping the SQL behind its figures