Skip to main content
PracticeHub exposes a Model Context Protocol server on every clinic domain. An AI client connects once, discovers the tools, and can then look things up, book and reschedule appointments, and create or update records — through the same API and the same rules as everything else on this site.

Discovers itself

list_entity_types describes every resource; the generic tools then read and write any of them. New resources appear automatically.

Two ways in

An API key for headless agents, or OAuth for AI apps acting for a signed-in team member.

Same rules

Tools call the API’s services, so an agent cannot do anything a person could not, and every action is on the audit trail.

​
Authentication

​
Protocol

Streamable HTTP: JSON-RPC 2.0 over POST, with Accept: application/json, text/event-stream. The usual sequence is initialize → tools/list → tools/call.

​
What an agent can do

  • Understand the clinic’s data — list_entity_types returns every resource with its attributes, what is filterable and sortable, and which write operations it accepts.
  • Find anything — query_entities with the API’s filter syntax, or the friendlier patient-lookup-tool for name / phone / email searches.
  • Change anything the API allows — write_entity for create / update / delete on any writable resource, plus curated appointment-book-tool and appointment-reschedule-tool for the common flows.
The Tools reference lists each tool with its parameters. Reads and writes are logged on the account’s Developers → API Logs page like any API request.
Tools return the API’s 422 / 409 messages as tool errors, so an agent that tries to book a deleted patient or double-process a visit is told exactly why and can correct itself.