Skip to content
FonteumThe Graph

By use case

Exclusion & monitoring (self-serve)Free roster screen — no accountExclusion & sanctions screeningCredentialing & provider-data enrichmentAudit evidence & defensible programsProvider data for AI / RAGM&A & network diligence

By buyer

Compliance & riskJournalists & newsroomsDevelopers & AI teams

By industry

HealthcareProviders & facilitiesSanctionsOFAC / EU / UK / UN / OIG / SAMFederal contractingSAM · USASpending · FAPIIS

The capability layer

APIREST + bulk accessFor AI agentsModel Context Protocol serverFHIR R4 APIBulk exportAudit packSigned report artifacts; source facts remain separately citedReconciliationSource-vs-source diffsAI answers with sourcesHow records link upHistoryRetained versions for named sources

The differentiator

Coverage & sourcesThe catalogFreshnessMethodologyCare CompareFacility qualityAI answers, comparedBrowse all datasets →
Research

The dev on-ramp

DocsAPI referenceConnect your AI agent (MCP)One-paste installFHIR sandboxLive API surfaceQuickstartStatusChangelogSDKs & integrations
Pricing
Sign inFree roster screen →Get a signed certificate →

Solutions

Exclusion & monitoring (self-serve)Exclusion & sanctions screeningCredentialing & provider-data enrichmentAudit evidence & defensible programsProvider data for AI / RAGM&A & network diligenceCompliance & riskJournalists & newsroomsDevelopers & AI teamsHealthcareSanctionsFederal contracting

Platform

APIFor AI agentsFHIR R4 APIBulk exportAudit packReconciliationAI answers with sourcesHow records link upHistory

Data

Coverage & sourcesFreshnessMethodologyCare CompareAI answers, comparedBrowse all datasets →
Research

Developers

DocsAPI referenceConnect your AI agent (MCP)FHIR sandboxQuickstartStatusChangelogSDKs & integrations
Pricing
Sign inFree roster screen →Get a signed certificate →

USE CASE · PROVIDER DATA FOR AI & RAG

Ground your AI agent in provider data it can cite back to the source.

A chunk-ready federal provider corpus with stable IDs and source metadata where available. Provenance fields are nullable and vary by endpoint, so governance reviews must inspect the fields actually returned.

Request access →Compliance & risk teamsSee the RAG chunks API →Developers & AI teams

9M+Source: CMS NPPES · As of 2026-06-10
providers within the active production registry (registry status is not completeness, load status, or freshness)Source-specific provenanceREST + MCP

✓ No PHI✓ Citation-stable chunk IDs✓ 14-field provenance✓ Deterministic re-pull

The AI-governance exposure

An ungrounded provider fact is a liability.

When a model answers with a provider's enrollment status, a sanction, or an NPI and cannot point to a source, that answer cannot be defended. In healthcare, an invented or stale provider fact is not a typo — it is a claim no one can stand behind. The fix is not a bigger model; it is retrieval where each chunk already carries its source and date.

Fonteum exposes source, snapshot, and methodology fields where the chunk builder has them. A grounded answer should cite only those returned fields; historical re-derivation also depends on whether the named source retains the relevant version.

The developer pain

Reference-heavy FHIR and index churn.

Raw FHIR JSON is reference-heavy — a Practitioner points to a PractitionerRole that points to an Organization that points to a Location — so building one chunk of context takes several round trips, and the coding-system URIs and extension blocks bloat every token budget. Worse, the raw files carry no chunk identity, so each re-pull re-embeds everything and churns your vector store.

One paginated GET returns pre-resolved, pre-chunked text with a stable chunk_id and the provenance block inline. The flattening, the chunking, and the citation are the response — not something you reconstruct downstream.


How it works

The corpus shape, and how a chunk stays citable.

Flat

Pre-resolved

Nested FHIR references are resolved server-side into a flat, fully-populated chunk — no client-side round trips to assemble context.

Stable

Chunk IDs

A deterministic chunk_id per record. Use it as the vector primary key; a re-pull upserts in place instead of duplicating vectors.

Nullable

Provenance fields

Source, source URL, snapshot date, last-checked date, methodology, and confidence appear where available; callers must preserve nulls and gaps.

MCP

Live agent path

The same graph is exposed as Model Context Protocol tools, so an agent can query live with the same provenance the static index carries.

Integration & workflow

One corpus. Two ways in.

Developers page the chunks endpoint into a vector store. Governance owners stand up a corpus where every retrieved fact carries a re-derivable citation. Same data, same provenance, same source snapshot.

GET /api/v1/rag/chunks

curl "https://fonteum.com/api/v1/rag/chunks?limit=50&cursor=0" \
  -H "Accept: application/json"

Response

{
  "total": 124817,
  "next_cursor": 50,
  "chunks": [
    {
      "chunk_id": "source:nppes#overview",
      "text": "The CMS NPPES registry enumerates US healthcare providers ...",
      "cite": "CMS NPPES, snapshot 2026-05-01",
      "source_url": "https://npiregistry.cms.hhs.gov/",
      "dataset_id": "nppes/v1",
      "provenance": {
        "_source": "CMS NPPES",
        "_source_url": "https://npiregistry.cms.hhs.gov/",
        "_snapshot": "2026-05-01",
        "_last_checked": "2026-06-17",
        "_methodology": "rag-chunks/v1",
        "_confidence": 1.0
      }
    }
  ]
}

Public endpoint, rate limited per source IP. Map each chunk to a LangChain Document or LlamaIndex TextNode — chunk_id as the id, text as the embed body, the provenance block as metadata. Full LangChain / LlamaIndex / MCP walkthroughs live in /docs/integrations.

  1. 01Page the corpus with ?limit= and the returned next_cursor — one deterministic GET per page, no language model in the pipeline.
  2. 02Map each chunk to a vector node: chunk_id as the primary key, text as the embed body, the provenance block as metadata.
  3. 03Embed and index. Because chunk IDs are stable, a later re-pull upserts in place rather than duplicating vectors.
  4. 04At answer time, carry the chunk's cite string and source_url into the response so every grounded fact footnotes its federal source.
  5. 05Keep the provenance record with the answer — the audit trail that shows a model-surfaced provider fact is real, dated, and re-derivable.

Sample audit-evidence artifact

RAG CITATION — PROVENANCE RECORD
Answer fact ......... NPI 1003894328 is enrolled in Medicare
Grounded on chunk ... source:pecos#1003894328
Source .............. CMS PECOS
Source URL .......... https://data.cms.gov/provider-enrollment
Source snapshot ..... 2026-05-01
Last checked (UTC) .. 2026-06-17T14:02:11Z
Methodology ......... rag-chunks/v1
Re-derivable ........ GET /api/v1/rag/chunks (deterministic chunk_id)

The provenance record is the governance artifact: it shows a model-surfaced provider fact, the chunk it was grounded on, and the federal source and snapshot it re-derives from.


Proof — not logos

Chunks expose the public-source metadata available to the endpoint.

9M+Source: CMS NPPES · As of 2026-06-10

Providers

Unique NPIs enumerated from the CMS NPI Registry — the identity backbone the corpus is chunked from.

CatalogSource: Fonteum methodology · As of 2026-07-12

Federal-source documentation

A documented catalog within the active production registry; registry status is not completeness, load status, or freshness. A retrieved chunk identifies its originating source and available snapshot metadata; coverage is bounded by the datasets exposed through this endpoint.

rag-chunks/v1

Methodology

Chunks can identify the chunking methodology version; reproducing a corpus also requires the same retained inputs and source release.

Source-cited

Evidence

Chunks carry their source and snapshot metadata when available. The 26.2M fact ledger currently has no deterministic claim-to-signature link.

“A retrieved fact is only as good as the source it carries. The chunk ID, the source, and the snapshot are the product.”

PROVIDER DATA FOR AI & RAG

Index a citation-stable provider corpus over REST or MCP.

Request access→ See a live sample response

Questions

Before the security questionnaire.

Why not just embed the raw NPPES and CMS files myself?

You can. The raw FHIR and CSV files are reference-heavy and carry no chunk identity, so a re-pull can churn your vector index. Fonteum returns pre-resolved, pre-chunked text with a stable chunk_id and the provenance fields available for that chunk; callers must handle null or absent source fields.

How does a chunk keep its citation?

A chunk can include source name, source URL, snapshot date, last-checked date, methodology version, and a cite string. Availability varies by source and endpoint, so carry only the metadata actually returned and do not infer missing fields.

Will the chunk IDs stay stable across pulls?

Yes. Chunk IDs are deterministic — the same record produces the same chunk_id on every pull, so an incremental re-pull upserts cleanly instead of duplicating vectors. Re-embedding only touches chunks whose underlying federal record actually changed.

Can my agent call this over MCP instead of REST?

Yes. The same provider graph is exposed as Model Context Protocol tools — search, resolve-by-NPI, exclusion check, dataset info, source list. MCP and REST responses expose route-specific provenance fields rather than a guaranteed tuple on every fact.

Is any patient data in the corpus?

No. The corpus is built only from public federal and state provider records keyed by NPI, CCN, and PECOS-ID. There is no PHI in the pipeline and none is required to index, retrieve, or cite a provider fact.

Go deeper

The data and platform behind the corpus.

Solutions

All solutions — by use case & buyer →

Guide

Healthcare data for AI / RAG — the full guide →

Platform

The capability layer — API, MCP, FHIR →

Developers

Docs, quickstart, and SDKs — the dev hub →

Data catalog

NPPES provider registry →

Data catalog

Browse catalogued federal datasets →

Research

Original studies built on the graph →

Use case

Credentialing & provider-data enrichment →

Use case

Exclusion & sanctions screening →

For developers

Fonteum for developers & AI teams →

FONTEUM · PROVIDER DATA FOR AI

Ground your agent on public data only. No PHI.

Request access→ Read the API docs

What’s on file, by the numbers

Platform snapshot · 2026-07-15

13.4Mproviders & companiesProviders, organizations, owners, and facilities on file
26.2Msource-linked factsSource-linked field facts in the dated platform snapshot
35sources liveCrosswalk-resolved sources with a snapshot in the preceding 45 days
111sources integratedActive registry rows; integration does not establish a load
13state Medicaid jurisdictionsDistinct states represented in the state-exclusions serving table

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

Published figures name their source and date.

Source and date

Published research identifies its government file and observation date. Source-file SHA-256 coverage is disclosed separately; facts do not currently link deterministically to signatures.

Reproducible SQL

Each study ships the exact query behind its figures, run against the same dated copy of the federal file we used. Re-run it yourself.

Daily observations

The platform records table row counts daily. Those observations detect local drift; they do not imply that an upstream publisher released or Fonteum ingested new data that day.

Named medical review

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

Read the full provenance and attestation methodology →

Fonteum
Platform
Platform overviewAPIFor AI agents (MCP)FHIR R4 APIBulk exportAudit packReconciliationAI answers with sourcesHow records link upHistory
Solutions
All solutionsExclusion & sanctions screeningCredentialing & enrichmentAudit evidenceProvider data for AI / RAGUse casesM&A & network diligenceCompliance & riskJournalists & newsroomsDevelopers & AI teams
Data & sources
Coverage & sourcesBrowse all datasetsState Medicaid exclusionsFreshnessMethodologyCare CompareNursing homesRecall recordsSanctions screeningOIG LEIE listOwnershipStaffingDeficienciesSpecial Focus Facilities
Federal contracting
OverviewAwards during active exclusionFederal debarment scorecardProcurement questionsContractor lookup8(a) certification guide
Developers
Developer hubDocsAPI referenceQuickstartStatusChangelogSDKs & integrationsWebhooks
Research & guides
Research hubLearnHow it worksGuidesHealthcare provider dataExclusion & sanctions screeningProvider credentialing dataHealthcare data for AIHospital margin gapProvider access gapsGlossaryComparisonsSourced data vs plain LLM answersCitationsManifestoWhy Fonteum
Company
AboutPressCustomersPricingContactEditorial policyCorrections
Trust & legal
TrustTrust markQualitySecurityPrivacy policyTerms of serviceAPI termsMedical disclaimer

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

© 2026 Fonteum LLC. All rights reserved.

·hello@fonteum.com

A public-records graph that exposes source and observation metadata where supplied.

Fonteum's provenance ledger contained 26.2M source-linked facts on July 12, 2026. All but 14 carried a source-file SHA-256; 0 linked deterministically to a signature. Inspect a supplied snapshot id at fonteum.com/verify · source-mark coverage and limitations.
Request access→