Skip to content

Connectors · Service desk & support

Humanitix MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Humanitix and the rest of your systems. It gives your agent 13 Humanitix actions (11 reads and 2 writes) and holds the Humanitix credential itself, so the agent never does. It paces Humanitix'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: "humanitix.events.list",  intent: "check which Humanitix account is connected"}# Get Events · read · 1 upstream call
  • 13actionsin one signed file
  • 11readlook, never change
  • 2writecreate and update
  • 0wait for a yesdestructive, confirmed first

Set up

Connect Humanitix 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 Humanitix.

    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_keyHumanitix API key
    account { op: "connections.requirements", service: "humanitix" }
    # 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: "humanitix.events.list" }# get events · read · 1 upstream callcheck { action: "humanitix.tickets.check_in", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Humanitix 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
Limits we pace to
200 calls a minute, per connection
API covered
Humanitix Public API 1.24.0api.humanitix.com
Built from
Humanitix's documentation, read 23 October 2026api.humanitix.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
11 of 11 reads, for up to 5 minutes; a write clears what it affects
Shared entities
3, so ask can line Humanitix up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Humanitix.

13 actions in 7 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 11readlook, never change
  • 2writecreate and update
  • 0destructivewait for a confirmation
  1. Tickets

    4

    2 read · 2 write · 0 destructive

    Get Tickets · Check in · Check out · Get Ticket

  2. Events

    2

    2 read · 0 write · 0 destructive

    Get Events · Get Event

  3. Orders

    2

    2 read · 0 write · 0 destructive

    Get Orders · Get Order

  4. Tags

    2

    2 read · 0 write · 0 destructive

    Get Tags · Get Tag

  5. Check in counts

    1

    1 read · 0 write · 0 destructive

    Get Event check in count (BETA)

  6. Global event dates

    1

    1 read · 0 write · 0 destructive

    Get Event Dates global

  7. Global events

    1

    1 read · 0 write · 0 destructive

    Get Events global

Top actions

The Humanitix API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 6 of Humanitix's 6 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
humanitix.events.listGet EventsGet Events.readcomm.event.list61 connectors
humanitix.orders.listGet OrdersGet Orders.readcommerce.order.list82 connectors
humanitix.tags.listGet TagsGet Tags.readcrm.tag.list65 connectors
humanitix.events.getGet EventGet Event.readcomm.event.get59 connectors
humanitix.orders.getGet OrderGet Order.readcommerce.order.get87 connectors
humanitix.tags.getGet TagGet Tag.readcrm.tag.get36 connectors
humanitix.tickets.listGet TicketsGet Tickets.readthis connector
humanitix.tickets.getGet TicketGet Ticket.readthis connector
humanitix.tickets.check_inCheck inCheck in.writethis connector
humanitix.tickets.check_outCheck outCheck out.writethis connector
humanitix.global_events.listGet Events globalGet Events global.readthis connector

Try it

Prompts to paste into Claude.

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

  1. Readread

    Which Humanitix orders from the last seven days are still unfulfilled?

    callshumanitix.orders.list

  2. Writewrite

    Check in in Humanitix. Show me exactly what you will send before you save it.

    callshumanitix.tickets.check_in

Governance for Humanitix

Every write can wait for a yes.

None of Humanitix's actions is destructive. A key can still be held to reads, capped, and set so a person confirms every write.

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.

a key for this connector
account {  op: "keys.create", name: "humanitix-agent",  allowed_actions: ["humanitix.*"], cap_calls: 2000,  confirm_policy: "human_for_writes"}
Illustrative. Scoped to Humanitix only, capped at 2,000 upstream calls, every write confirmed.

Cost

What Humanitix costs on actionlake.

Every Humanitix action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Humanitix 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 13 Humanitix actions
  • 13actions pageeach page of a long list is one call
  • 11reads 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 Humanitix action.

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

Tickets4
  • humanitix.tickets.check_inCheck inwrite
  • humanitix.tickets.check_outCheck outwrite
  • humanitix.tickets.getGet Ticketread
  • humanitix.tickets.listGet Ticketsread
Events2
  • humanitix.events.getGet Eventread
  • humanitix.events.listGet Eventsread
Orders2
  • humanitix.orders.getGet Orderread
  • humanitix.orders.listGet Ordersread
Tags2
  • humanitix.tags.getGet Tagread
  • humanitix.tags.listGet Tagsread
Check in counts1
  • humanitix.check_in_counts.getGet Event check in count (BETA)read
Global event dates1
  • humanitix.global_event_dates.listGet Event Dates globalread
Global events1
  • humanitix.global_events.listGet Events globalread

Questions

The Humanitix MCP server, answered.

Is there a Humanitix MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 13 Humanitix actions across tickets, events, orders and tags, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Humanitix.

What do I need to connect Humanitix?

Humanitix API key. The free call account { op: "connections.requirements", service: "humanitix" } lists exactly what to paste.

Can an AI agent change things in Humanitix?

Only if its key allows it. 2 Humanitix actions write, and none is destructive. A key can be limited to reads, capped, and set so a person confirms every write.

Will an AI agent use up my Humanitix API limit?

actionlake paces every call to the limits in the Humanitix service file: 200 calls a minute per connection. Repeated reads are answered from cache (11 Humanitix actions can be), which never reaches Humanitix.

What does a Humanitix action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (13 Humanitix actions page). Cache hits, searches, dry runs and calls Humanitix 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 Humanitix API does it cover?

The Humanitix Public API 1.24.0 at api.humanitix.com. It is built from Humanitix's documentation as read on 23 October 2026. 13 actions in 7 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Humanitix data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, 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 Humanitix 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 Humanitix today.

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