Skip to content

Connectors · Marketing & media

Livestorm MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Livestorm and the rest of your systems. It gives your agent 41 Livestorm actions (22 reads, 12 writes and 7 that wait for a confirmation) and holds the Livestorm credential itself, so the agent never does. It paces Livestorm'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: "livestorm.organization.get",  intent: "check which Livestorm account is connected"}# Get the current organization · read · 1 upstream call
  • 41actionsin one signed file
  • 22readlook, never change
  • 12writecreate and update
  • 7wait for a yesdestructive, confirmed first

Set up

Connect Livestorm 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 Livestorm.

    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_tokenLivestorm API token
    account { op: "connections.requirements", service: "livestorm" }
    # 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: "livestorm.organization.get" }# get the current organization · read · 1 upstream callcheck { action: "livestorm.events.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Livestorm 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_token
Limits we pace to
5 calls a second, per connection
API covered
Livestorm API v1api.livestorm.co/v1
Built from
Livestorm's documentation, read 23 October 2026developers.livestorm.codevelopers.livestorm.co
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
22 of 22 reads, for up to an hour; a write clears what it affects
Shared entities
3, so ask can line Livestorm up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Livestorm.

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

  • 22readlook, never change
  • 12writecreate and update
  • 7destructivewait for a confirmation
  1. Webinars

    41

    22 read · 12 write · 7 destructive

    List events · List team members · List people · Create an event

Top actions

The Livestorm API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 24 of Livestorm's 25 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
livestorm.events.listList eventsList the events of your workspace.readcomm.event.list61 connectors
livestorm.users.listList team membersList organization team members.readidentity.user.list474 connectors
livestorm.people.listList peopleList all the people belonging to your workspace, who engaged with one of your event sessions at some point, including your team members.readcrm.contact.list177 connectors
livestorm.events.createCreate an eventCreate a new event or duplicate an existing one.writecomm.event.create52 connectors
livestorm.events.deleteDelete an eventDelete a single event.destructivecomm.event.delete45 connectors
livestorm.users.createCreate a team memberCreate a new team member user.writeidentity.user.create262 connectors
livestorm.people.getGet a personRetrieve someone's details.readcrm.contact.get176 connectors
livestorm.session_chat_messages.listList the chat messages of a sessionList all the chat messages of a session.readcomm.message.list42 connectors
livestorm.me.getGet the current userGet the currently connected user (only supported with OAuth2) and organization.readidentity.current_user.get307 connectors
livestorm.session_people.updateUpdate someone's registration for a sessionUpdate a contact's registration data for a specific session. This endpoint allows updating UTM tracking data (referrer, utm_source, utm_medium, etc.) and…writecomm.event_attendee.update9 connectors
livestorm.event_people.listList the people of an eventList all the people linked to all the sessions of an event.readcomm.event_attendee.list12 connectors
livestorm.session_recordings.listList the recordings of a sessionList all the recordings of a session.readcomm.meeting_recording.list11 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

    Find the Livestorm contacts with no email address, so we can clean them up.

    callslivestorm.people.list

  2. Writewrite

    Create an event in Livestorm. Show me exactly what you will send before you save it.

    callslivestorm.events.create

  3. Across systemsread

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

    callslivestorm.people.listhalopsa.users.list

Across your systems

Livestorm, joined to the rest of your business.

One ask fetches from Livestorm 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 Livestorm and HaloPSA, and how many are in only one of them?

    livestorm.people.list + halopsa.users.list, on crm.contact · HaloPSA

  • Which contacts are in both Livestorm and NetSuite, and how many are in only one of them?

    livestorm.people.list + netsuite.views.contacts, on crm.contact · NetSuite

Also mapped by other connectorsidentity.user 517crm.contact 192comm.event 47
ask
ask {  intent: "which contacts are in both Livestorm and HaloPSA, and how many are in only one of them",  steps: [    { action: "livestorm.people.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 Livestorm

Destructive actions wait for a yes.

7 Livestorm actions are destructive. These are all of them:

  • Delete an eventlivestorm.events.delete
  • Delete a team memberlivestorm.users.delete
  • Remove someone from a sessionlivestorm.session_people.delete
  • Delete a webhooklivestorm.webhooks.delete
  • Delete a sessionlivestorm.sessions.delete
  • Remove someone from a session by emaillivestorm.session_people.delete_by_email
  • Remove a tag from an eventlivestorm.event_tags.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.

dolivestorm.events.deleteconfirm_policy: human

Delete an event?

intent: the user asked me to delete an event

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

Cost

What Livestorm costs on actionlake.

Every Livestorm action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Livestorm 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 41 Livestorm actions
  • 41actions pageeach page of a long list is one call
  • 22reads 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 Livestorm action.

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

Webinars41
  • livestorm.event_people.getGet someone's details for an eventread
  • livestorm.event_people.listList the people of an eventread
  • livestorm.event_sessions.createCreate an event sessionwrite
  • livestorm.event_sessions.listList the sessions of an eventread
  • livestorm.event_tags.createAssign a tag to an eventwrite
  • livestorm.event_tags.deleteRemove a tag from an eventdestructive
  • livestorm.events.createCreate an eventwrite
  • livestorm.events.deleteDelete an eventdestructive
  • livestorm.events.getGet an eventread
  • livestorm.events.listList eventsread
  • livestorm.events.replaceFully update an eventwrite
  • livestorm.events.updatePartially update an eventwrite
  • livestorm.job_tasks.listList the tasks of a jobread
  • livestorm.jobs.getGet a jobread
  • livestorm.me.getGet the current userread
  • livestorm.organization.getGet the current organizationread
  • livestorm.people.getGet a personread
  • livestorm.people.listList peopleread
  • livestorm.people_attributes.listList people attributesread
  • livestorm.ping.getTest authenticationread
  • livestorm.session_chat_messages.listList the chat messages of a sessionread
  • livestorm.session_people.bulk_createRegister many people for a session (job)write
  • livestorm.session_people.createRegister someone for a sessionwrite
  • livestorm.session_people.deleteRemove someone from a sessiondestructive
  • livestorm.session_people.delete_by_emailRemove someone from a session by emaildestructive
  • livestorm.session_people.getGet someone's details for a sessionread
  • livestorm.session_people.listList the people of a sessionread
  • livestorm.session_people.updateUpdate someone's registration for a sessionwrite
  • livestorm.session_questions.listList the questions of a sessionread
  • livestorm.session_recordings.listList the recordings of a sessionread
  • livestorm.sessions.deleteDelete a sessiondestructive
  • livestorm.sessions.getGet a sessionread
  • livestorm.sessions.listList sessionsread
  • livestorm.sessions.replaceFully update a sessionwrite
  • livestorm.sessions.updatePartially update a sessionwrite
  • livestorm.users.createCreate a team memberwrite
  • livestorm.users.deleteDelete a team memberdestructive
  • livestorm.users.listList team membersread
  • livestorm.webhooks.createCreate a webhookwrite
  • livestorm.webhooks.deleteDelete a webhookdestructive
  • livestorm.webhooks.listList webhooksread

Questions

The Livestorm MCP server, answered.

Is there a Livestorm MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 41 Livestorm actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Livestorm.

What do I need to connect Livestorm?

Livestorm API token. The free call account { op: "connections.requirements", service: "livestorm" } lists exactly what to paste.

Can an AI agent delete or change things in Livestorm?

Only if its key allows it, and only with an explicit confirmation. 7 Livestorm actions are destructive, including delete an event, delete a team member and remove someone from a session. 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 Livestorm API limit?

actionlake paces every call to the limits in the Livestorm service file: 5 calls a second per connection. Repeated reads are answered from cache (22 Livestorm actions can be), which never reaches Livestorm.

What does a Livestorm action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (41 Livestorm actions page). Cache hits, searches, dry runs and calls Livestorm 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 Livestorm API does it cover?

The Livestorm API v1 at api.livestorm.co/v1. It is built from Livestorm's documentation as read on 23 October 2026. 41 actions in 1 area, each one in the signed service file (version 1.0.0).

Can I combine Livestorm with my other systems?

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

Does actionlake keep my Livestorm 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 Livestorm 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 Livestorm today.

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