FHIR R4 · bulk export · MCP
- 5 USCDI v3 resources
FHIR R4 US Core 6.1.0
REST provider API
5 distinct USCDI v3 Provider resources — Practitioner, PractitionerRole, Organization, Location, HealthcareService — with US Core search parameters. Provenance tags are nullable and vary by resource and response. SMART Backend Services auth (JWT / RS384). The CapabilityStatement at /api/fhir/metadata is the discovery entry point.
- Async NDJSON $export
HL7 Bulk Data Access
Async $export
HL7 FHIR R4 Bulk Data Access ($export) — Inngest-backed async job queue, status polling, and NDJSON output per resource type. SMART Backend Services auth. Directly loadable by Spark, Pandas, DuckDB, and BigQuery for population-scale jobs.
- MCP + agent card
MCP server
Agentic workflows
A Model Context Protocol server exposing Fonteum's provider-data and exclusion-lookup tools to AI agents, plus an agent card at /.well-known/agent.json with the full skills inventory for Google ADK, LangGraph, and BeeAI consumers. LangChain and LlamaIndex adapters are documented at /docs/integrations.
Standards-conformant. Provenance-tagged. Agent-ready.
FHIR R4 US Core 6.1.0 — full USCDI v3 Provider conformance
The FHIR surface exposes Practitioner, PractitionerRole, Organization, Location, and HealthcareService resources. The CapabilityStatement at /api/fhir/metadata enumerates the supported interactions. The loaded NPPES layer contains active provider records; the wider active production registry does not establish loaded, complete, or fresh coverage.
Provenance fields where supplied
FHIR and export surfaces expose nullable source, date, method, and integrity fields where the underlying route supplies them. Coverage varies by resource, record, and export, so consumers must inspect the actual response and must not infer a missing citation, date, digest, or signature link.
Agent-native via MCP
An MCP server exposes provider-data and exclusion-lookup tools — including the “excluded anywhere” check over the OIG LEIE () and companion lists — so an agent calls a tool instead of writing HTTP glue. The agent card at /.well-known/agent.json publishes the skills inventory that Google ADK, LangGraph, and BeeAI parse, and dependency-free LangChain and LlamaIndex adapters are documented at /docs/integrations.
Discover · Authenticate · Consume
Discover
Probe the CapabilityStatement at /api/fhir/metadata to enumerate the 5 USCDI v3 Provider resources, their US Core search parameters, and the SMART Backend Services auth profile in the security extension. For agents, read the agent card at /.well-known/agent.json for the skills inventory. Reference docs live at /docs/fhir, /docs/bulk-export, and /docs/integrations.
Authenticate
Exchange a JWT client assertion signed with RS384 for a short-lived bearer token via SMART Backend Services — no interactive login. One credential covers the REST resource endpoints and the asynchronous bulk $export, so server-side ETL, scheduled jobs, and agent runtimes integrate the same way.
Consume
Query individual FHIR resources, run an async NDJSON $export for population-scale loads, or call the MCP tools from an agent. Responses expose a nullable provenance schema; populated source and observation fields vary by endpoint and record. Build on a graph of active providers — free on the public surface, with dedicated throughput available via the pilot tier.
Common questions
- What FHIR resources does Fonteum's API expose?
- Fonteum implements HL7 FHIR R4 against US Core 6.1.0, exposing 5 distinct USCDI v3 Provider resources: Practitioner, PractitionerRole, Organization, Location, and HealthcareService. Each is reachable through individual reads and supported search parameters and returns application/fhir+json. Provenance tags are nullable and populated fields vary by resource and response. The CapabilityStatement at /api/fhir/metadata enumerates the supported interactions and SMART auth profile. The reference documentation is at /docs/fhir. The NPPES layer contains active provider records.
- How does SMART Backend Services authentication work?
- Fonteum supports the SMART App Launch Backend Services profile for unattended system-to-system access. The flow is a JSON Web Token (JWT) client assertion signed with RS384, exchanged at the token endpoint for a short-lived bearer access token — no interactive user login, which is what server-side ETL, scheduled jobs, and agent runtimes need. The CapabilityStatement at /api/fhir/metadata declares the supported auth flows in its security extension, so a consuming system can discover the token endpoint and scopes programmatically before exchanging credentials. The same auth profile covers both the REST resource endpoints and the asynchronous Bulk Data Access $export, so a single credential serves both individual queries and population-scale extracts. This is the auth pattern expected by integrations that follow SMART-on-FHIR conformance, including those built against CMS interoperability obligations.
- How does the bulk NDJSON export work?
- A $export request starts an asynchronous NDJSON job and returns a manifest when the job completes. The requested scope and available resource types determine the files returned. Provenance tags are nullable and vary by resource; consumers must inspect each line rather than assume a complete tuple. The manifest records the counts and export timestamp supplied by that job. SMART Backend Services auth secures unattended access. The reference is at /docs/bulk-export.
- Does Fonteum provide an MCP server for AI agents?
- Yes. Fonteum ships a Model Context Protocol (MCP) server with provider-data and exclusion-lookup tools, including the loaded OIG LEIE serving table ( rows from the May 8 source release when checked July 12). Results expose the nullable source and observation metadata supplied by the underlying route; individual hits do not universally inherit a complete provenance tuple or signature link. The agent card at /.well-known/agent.json publishes the current skills inventory, and integration notes are at /docs/integrations.
- Are there rate limits and integrity headers on the API?
- Yes. Public export endpoints apply a per-IP rate limit to keep the free surface available, and CSV and dataset exports return integrity headers — an X-Fonteum-SHA256 content hash and an X-Fonteum-Methodology-Version header — so a consumer can confirm the bytes it received and the methodology version they were produced under. The FHIR REST and bulk endpoints use SMART Backend Services auth for higher-throughput, unattended access; the asynchronous $export pattern itself is the mechanism for population-scale loads, so large jobs run as background work rather than against a synchronous request limit. The current limits and header semantics for each endpoint are documented at /docs/fhir and /docs/bulk-export. For production workloads that need dedicated throughput or a custom export cadence, the pilot tier provides scoped access starting at $2,500/mo.
- Is the API free, and what does the pilot tier add?
- Public provider pages, selected research downloads, FHIR routes, and the MCP server expose the access described in their current documentation. The /sources catalog states publisher cadence and redistribution posture where recorded, but catalog presence and do not establish a loaded, complete, or fresh dataset. The scoped pilot tier, starting at $2,500/mo, adds contracted throughput, scoped exports, and integration support; exported provenance fields remain source-specific and nullable.
Start with the technical docs.
FHIR R4 reference at /docs/fhir, bulk export at /docs/bulk-export, and agent integrations at /docs/integrations. Pilot tier from $2,500/mo.
- /docs/fhir → FHIR R4 US Core 6.1.0 endpoint reference and CapabilityStatement.
- /docs/bulk-export → HL7 Bulk Data Access $export endpoint reference.
- /docs/integrations → MCP server, LangChain, and LlamaIndex adapters.
- /use-cases/government-contractors → Federal-integration patterns for CMS, VA, and OIG.