The Nextvisit workspace is an open clinical surface. API keys, OAuth, and MCP each give a different kind of caller the same workspace-scoped view of patients, encounters, notes, and codes. PHI access stays inside the workspace boundary on every path.
A custom analytics job, a partner app, or an AI assistant each have different shapes. Each method below carries the same workspace scope and the same audit trail.
Workspace-scoped REST keys generated under Settings, Tools and AI. Drive analytics, internal automation, and custom tools against the same data your clinicians see. Every call carries the workspace boundary, so no key ever reads across tenants.
Standard OAuth 2.0 flow for third-party apps that need delegated access. Users grant explicit consent, scopes are reviewed up front, and tokens carry the same workspace boundary as a key. Use it for partner apps and any tool with its own user surface.
Nextvisit exposes its workspace as a Model Context Protocol server. MCP-aware AI assistants connect directly and read structured clinical data through a typed tool surface, no custom integration build per assistant. Bring your own AI on top of the chart.
Model Context Protocol is an open standard for letting AI assistants read structured data through a typed tool surface, instead of every assistant getting a one-off integration build.
Anthropic published MCP, OpenAI adopted it, and most local LLM runtimes support it now. Nextvisit exposes its workspace as an MCP server. An MCP-aware assistant connects once, then reads patients, encounters, notes, and codes through a small set of typed tools. The same workspace scope you use for API keys and OAuth applies here too.
The practical effect: a clinician can point Claude, ChatGPT, or a local model at their workspace and ask clinical questions against real chart data, without anyone writing a custom integration for that assistant. Tool calls return structured JSON, so the assistant reasons over fields instead of scraping a UI.
// Assistant invokes a Nextvisit MCP tool
query_encounters({
patient_id: "pat_018f...c1",
range: { from: "2026-01-01", to: "2026-05-01" },
include: ["note", "codes", "peer_review"]
})
// Returns
{
"encounters": [
{
"id": "enc_a1b2",
"date": "2026-04-18T14:32:00Z",
"status": "signed",
"codes": ["F33.1", "F41.1"],
"note": "..."
}
]
}Illustrative shape, not the verified call signature. See the MCP guide for the live tool list and field reference.
Standard bearer auth over HTTPS. Generate the key under Settings, Tools and AI, then call any documented endpoint with it.
# List signed encounters for a patient over a date range
curl -sS \
-H "Authorization: Bearer nv_live_8f2c...41a" \
-H "Accept: application/json" \
"https://api.nextvisit.ai/v1/encounters?patient_id=pat_018f...c1&status=signed&from=2026-01-01"
# Response (truncated)
{
"data": [
{
"id": "enc_a1b2",
"signed_at": "2026-04-18T14:42:11Z",
"provider_id": "prv_77a3",
"codes": ["F33.1", "F41.1"]
}
],
"next_cursor": "eyJvZmZzZXQiOjUwfQ"
}Illustrative endpoint and key shape. The live API reference covers pagination, rate limits, and the full resource list.
Notes from a Pocket or Plaud AI device flow into the workspace automatically. No license fee, no add-on cost. The same recording auto-links to the right chart if the patient name and DOB are spoken in the first minute.
The heypocket.com hardware recorder pairs with the workspace and posts each recording on completion. AriaMD generates a note in the assigned template just like a live session.
Auto-link tip: say the patient name and date of birth in the first minute. The encounter attaches to the right chart on import.
Plaud AI pin and Plaud Note recordings sync into the workspace automatically. Useful for clinicians who already carry one for personal capture.
Auto-link tip: same convention applies. The patient name and DOB at the top of the recording trigger automatic chart attachment.
The push side of the workspace. Already covered in detail on the features page.
Notes, codes, and bundles flow out of Nextvisit to the EHRs behavioral health practices actually use. FHIR R4 and HL7 v2 cover most stacks, partner integrations cover the rest, and a copy-out plus fax fallback handles the long tail. The full destination list, the bundle layout, and the live push state are documented on the features page.
We run a mock session live, draft the note, and walk through what the downstream claim would look like. No slides. No sales deck.