Healthpoint MCP Server

Most knowledge and memory work still happens through a UI a human drives. Healthpoint MCP server moves it into the conversation instead. Read-only MCP server for licensed Healthpoint HL7 FHIR API access.

The short version

Rust-first tooling for the Healthpoint HL7 FHIR® API: a typed client, CLI, read-only MCP server, and future open-social-data adapter.

The tools it exposes

The server publishes 10 tools. What each one is for:

• healthpoint.diagnostic.status — Show redacted runtime mode, configuration, and readiness
• healthpoint.access.notes — Show non-secret endpoint, auth, and documentation notes
• healthpoint.access.policy — Show the conservative access/export policy before reuse
• healthpoint.services.search — Search HealthcareService records by text, codes, region filters, cursor, and limit
• healthpoint.services.search_snomed — Search HealthcareService records by SNOMED CT code in type, category, or specialty
• healthpoint.services.nearby — Find HealthcareService records near a latitude/longitude point
• healthpoint.service.get — Read one HealthcareService by FHIR id
• healthpoint.location.get — Read one Location by FHIR id
• healthpoint.organization.get — Read one Organization by FHIR id
• healthpoint.resource.read — Read a supported healthpoint:// resource URI

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What it needs from you

Configuration is passed through the environment: HEALTHPOINT_MODE, HEALTHPOINT_API_KEY, HEALTHPOINT_BASE_URL, HEALTHPOINT_AUTH_SCHEME, HEALTHPOINT_GEO_SEARCH_MODE, HEALTHPOINT_TIMEOUT_SECS, HEALTHPOINT_EXPORT_POLICY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Healthpoint's toolset — healthpoint.diagnostic.status, healthpoint.access.notes, healthpoint.access.policy and 7 more — is a fair guide to whether it matches your workflow. It is maintained by edithatogo; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Healthpoint.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.