Skip to content

Connectors · Accounting & finance

Healthie MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Healthie and the rest of your systems. It gives your agent 723 Healthie actions (306 reads, 301 writes and 116 that wait for a confirmation) and holds the Healthie credential itself, so the agent never does. It paces Healthie's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "healthie.users.list",  intent: "check which Healthie account is connected"}# List users · read · 1 upstream call
  • 723actionsin one signed file
  • 306readlook, never change
  • 301writecreate and update
  • 116wait for a yesdestructive, confirmed first

Set up

Connect Healthie in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect Healthie.

    API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_keyHealthie API key
    • hostWhere your Healthie lives: your host
    • shardYour Healthie shard
    account { op: "connections.requirements", service: "healthie" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "healthie.users.list" }# list users · read · 1 upstream callcheck { action: "healthie.clients.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Healthie at a glance

Sign-in
API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_key
Setup fields
hostshard
Limits we pace to
600 calls a minute, per connection
API covered
Healthie (EHR, telehealth and practice management) API 2026-10-01api.gethealthie.com
Built from
Healthie's documentation, read 23 October 2026docs.gethealthie.comdocs.gethealthie.comdocs.gethealthie.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
299 of 306 reads, for up to an hour; a write clears what it affects
Shared entities
5, so ask can line Healthie up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Healthie.

723 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 306readlook, never change
  • 301writecreate and update
  • 116destructivewait for a confirmation
  1. Healthie

    723

    306 read · 301 write · 116 destructive

    List users · Create client · Update client · List tasks

Top actions

The Healthie API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 74 of Healthie's 74 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
healthie.users.listList usersFetch paginated patients collection (use organizationMembers query for providers)readidentity.user.list474 connectors
healthie.clients.createCreate clientCreate a Clientwritecrm.contact.create161 connectors
healthie.clients.updateUpdate clientUpdate Clientwritecrm.contact.update159 connectors
healthie.tasks.listList tasksAll tasks assigned to a provider or clientreadwork.task.list122 connectors
healthie.users.getGet userFetch a user by IDreadidentity.user.get399 connectors
healthie.billing_items.listList billing itemsFetch paginated Billing Items collectionreadfinance.billing_item.list24 connectors
healthie.tasks.createCreate taskCreate a task for providerwritework.task.create127 connectors
healthie.user_groups.listList user groupsCursor-paginated user groups owned by the current user.readidentity.group.list262 connectors
healthie.tags.listList tagsA collection of tags related to current patient/provider/organizationreadcrm.tag.list65 connectors
healthie.tags.createCreate tagCreate a custom user tagwritecrm.tag.create49 connectors
healthie.locations.listList locationsGet locations for a given user (or current user)readcrm.location.list48 connectors
healthie.tasks.deleteDelete taskDestroy a taskdestructivework.task.delete107 connectors

Try it

Prompts to paste into Claude.

Each one names the Healthie actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Which Healthie tasks are overdue, and who owns each one?

    callshealthie.tasks.list

  2. Writewrite

    Create client in Healthie. Show me exactly what you will send before you save it.

    callshealthie.clients.create

  3. Across systemsread

    Which contacts are in both Healthie and HaloPSA, and how many are in only one of them?

    callshealthie.users.listhalopsa.users.list

Across your systems

Healthie, joined to the rest of your business.

One ask fetches from Healthie and another system, joins the rows on the same customer on our side, and hands your agent the answer, not every row.

  • Which contacts are in both Healthie and HaloPSA, and how many are in only one of them?

    healthie.users.list + halopsa.users.list, on crm.contact · HaloPSA

  • Which contacts are in both Healthie and HubSpot CRM, and how many are in only one of them?

    healthie.users.list + hubspot_crm.contacts.list, on crm.contact · HubSpot CRM

Also mapped by other connectorsidentity.user 517crm.contact 192work.task 105finance.billing_item 14service.service_appointment 9
ask
ask {  intent: "which contacts are in both Healthie and HaloPSA, and how many are in only one of them",  steps: [    { action: "healthie.users.list", as: "people", input: {}, limit: 100, max_pages: 5 },    { action: "halopsa.users.list", as: "people2", input: {}, limit: 100, max_pages: 5 },    { join: {        left: "people",        right: "people2",        on: "crm.contact",        group_by: "people.email",        select: ["people.email", "count(people2.id) as in_halopsa"]    } }  ]}
Example. Run it through check first: it validates the steps and prices them, and it is free.

Governance for Healthie

Destructive actions wait for a yes.

116 Healthie actions are destructive. The first 10:

  • Delete taskhealthie.tasks.delete
  • Delete user grouphealthie.user_groups.delete
  • Delete taghealthie.tags.delete
  • Delete locationhealthie.locations.delete
  • Delete api keyhealthie.api_keys.delete
  • Delete billing itemhealthie.billing_items.delete
  • Delete appointmenthealthie.appointments.delete
  • Delete producthealthie.products.delete
  • Delete folderhealthie.folders.delete
  • Delete webhookhealthie.webhooks.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dohealthie.tasks.deleteconfirm_policy: human

Delete task?

intent: the user asked me to delete task

run suspended · waiting for a named person · key healthie-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "healthie-agent",  allowed_actions: ["healthie.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "healthie.tasks.delete", approver: "[email protected]" },    { match: "healthie.user_groups.delete", approver: "[email protected]" },    { match: "healthie.tags.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Healthie only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Healthie costs on actionlake.

Every Healthie action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Healthie refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 723 Healthie actions
  • 116actions pageeach page of a long list is one call
  • 299reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Healthie action.

723 actions by area: the id your agent calls, what it does, and its effect.

Healthie723
  • healthie.clients.createCreate clientwrite
  • healthie.clients.updateUpdate clientwrite
  • healthie.tasks.listList tasksread
  • healthie.users.listList usersread
  • healthie.accepted_insurance_plans.createCreate accepted insurance planwrite
  • healthie.accepted_insurance_plans.deleteDelete accepted insurance plandestructive
  • and 717 more in this area

This index shows a sample of each area. All 723 actions, with their inputs and prices, are in the catalogue, which a free sandbox key can search.

Questions

The Healthie MCP server, answered.

Is there a Healthie MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 723 Healthie actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Healthie.

What do I need to connect Healthie?

Healthie API key. Plus your host and your shard. The free call account { op: "connections.requirements", service: "healthie" } lists exactly what to paste.

Can an AI agent delete or change things in Healthie?

Only if its key allows it, and only with an explicit confirmation. 116 Healthie actions are destructive, including delete task, delete user group and delete tag. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Healthie API limit?

actionlake paces every call to the limits in the Healthie service file: 600 calls a minute per connection. Repeated reads are answered from cache (299 Healthie actions can be), which never reaches Healthie.

What does a Healthie action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (116 Healthie actions page). Cache hits, searches, dry runs and calls Healthie refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Healthie API does it cover?

The Healthie (EHR, telehealth and practice management) API 2026-10-01 at api.gethealthie.com by default, or the base URL set when you connect. It is built from Healthie's documentation as read on 23 October 2026. 723 actions in 1 area, each one in the signed service file (version 1.0.0).

Can I combine Healthie with my other systems?

Yes. ask joins Healthie to HaloPSA or HubSpot CRM on the same customer and returns the answer rather than every row. Healthie maps crm.contact, which 192 other connectors also map.

Does actionlake keep my Healthie data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Healthie credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Healthie today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.