Skip to content

Connectors · MSP & PSA

Action1 MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Action1 and the rest of your systems. It gives your agent 135 Action1 actions (70 reads, 44 writes and 21 that wait for a confirmation) and holds the Action1 credential itself, so the agent never does. It paces Action1'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: "action1.organizations.list",  intent: "check which Action1 account is connected"}# List organizations · read · 1 upstream call
  • 135actionsin one signed file
  • 70readlook, never change
  • 44writecreate and update
  • 21wait for a yesdestructive, confirmed first

Set up

Connect Action1 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 Action1.

    Session login. actionlake opens the session and renews it when it expires. actionlake stores what you paste write-only, sealed under your tenant's key.

    • client_idAction1 API Client ID (Configuration > API Credentials in the Action1 console)
    • client_secretAction1 API Client Secret, shown once when the API credential is created
    • hostWhere your Action1 lives: your host
    account { op: "connections.requirements", service: "action1" }
    # 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: "action1.organizations.list" }# list organizations · read · 1 upstream callcheck { action: "action1.users.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Action1 at a glance

Sign-in
Session login. actionlake opens the session and renews it when it expires.
You provide
client_idclient_secret
Setup fields
host
Limits we pace to
300 calls a minute, per connection
API covered
Action1 API 3.0 (OpenAPI 3.1.0), at your Action1 instance's API base URL, which you enter when connecting (path /api/3.0)
Built from
Action1's documentation, read 23 October 2026app.action1.comaction1.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
70 of 70 reads, for up to 5 minutes; a write clears what it affects
Shared entities
3, so ask can line Action1 up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Action1.

135 actions in 27 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 70readlook, never change
  • 44writecreate and update
  • 21destructivewait for a confirmation
  1. Automations

    13

    7 read · 3 write · 3 destructive

    Run an automation now · List automation instances · Create a scheduled automation · List scheduled automations

  2. Packages

    13

    5 read · 5 write · 3 destructive

    Clone a software repository package · Create a software repository package · List software repository packages · List package match conflicts

  3. Endpoints

    11

    6 read · 4 write · 1 destructive

    List managed endpoints · Get a managed endpoint · Update a managed endpoint · Delete a managed endpoint

  4. Roles

    9

    3 read · 4 write · 2 destructive

    List roles · Create a role · Get a role · Update a role

  5. Endpoint groups

    7

    3 read · 3 write · 1 destructive

    Create an endpoint group · List endpoint groups · List endpoints in a group · Get an endpoint group

  6. Vulnerabilities

    7

    4 read · 2 write · 1 destructive

    List vulnerabilities · List endpoints affected by a CVE · Create a CVE remediation · List a CVE's remediations

  7. Me

    6

    2 read · 3 write · 1 destructive

    Create a report subscription · List my report subscriptions · Get the current API user · Update the current user's profile

  8. Subscription

    6

    4 read · 2 write · 0 destructive

    Request a subscription quote · Request an enterprise trial · Get the enterprise subscription · List license usage per organization

19 more areas · 63 actions
  • Users 6
  • Data sources 5
  • Installed software 5
  • Reports 5
  • Scripts 5
  • Settings 5
  • Deployers 4
  • Enterprise 4
  • Organizations 4
  • Report data 4
  • Updates 4
  • Action templates 2
  • Agent deployment 2
  • Audit events 2
  • Setting templates 2
  • Cve descriptions 1
  • Logs 1
  • Permissions 1
  • Search 1

Top actions

The Action1 API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 15 of Action1's 15 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
action1.users.listList usersListing users.readidentity.user.list474 connectors
action1.endpoints.listList managed endpointsListing all endpoints.readdevice.endpoint.list65 connectors
action1.organizations.listList organizationsListing organizations.readcrm.company.list162 connectors
action1.users.createCreate a userCreate new user.writeidentity.user.create262 connectors
action1.users.deleteDelete a userDelete user.destructiveidentity.user.delete253 connectors
action1.endpoints.getGet a managed endpointGetting a specific endpoint.readdevice.endpoint.get57 connectors
action1.roles.listList rolesListing roles.readidentity.role.list184 connectors
action1.roles.createCreate a roleCreating a role.writeidentity.role.create105 connectors
action1.updates.getList missing update versions for a packageListing updates for a package.readthis connector
action1.updates.listList missing updatesListing missing updates.readthis connector
action1.organizations.createCreate an organizationCreate an organization.writethis connector
action1.vulnerabilities.listList vulnerabilitiesList of all vulnerable software within the organization.readthis connector

Try it

Prompts to paste into Claude.

Each one names the Action1 actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Which Action1 devices have not checked in for a week?

    callsaction1.endpoints.list

  2. Writewrite

    Create a user in Action1. Show me exactly what you will send before you save it.

    callsaction1.users.create

  3. Across systemsread

    Which Action1 companies have invoices in NetSuite, and how many each?

    callsaction1.organizations.listnetsuite.views.invoices

Across your systems

Action1, joined to the rest of your business.

One ask fetches from Action1 and another system, joins the rows on the same customer on our side, and hands your agent the answer, not every row.

  • Which Action1 companies have invoices in NetSuite, and how many each?

    action1.organizations.list + netsuite.views.invoices, on crm.company · NetSuite

  • Which Action1 companies have tickets in HubSpot CRM, and how many each?

    action1.organizations.list + hubspot_crm.tickets.list, on crm.company · HubSpot CRM

Also mapped by other connectorsidentity.user 517crm.company 227device.endpoint 69
ask
ask {  intent: "which Action1 companies have invoices in NetSuite, and how many each",  steps: [    { action: "action1.organizations.list", as: "co", input: {}, limit: 100, max_pages: 5 },    { action: "netsuite.views.invoices", as: "inv", input: {}, limit: 100, max_pages: 5 },    { join: {        left: "co",        right: "inv",        on: "crm.company",        group_by: "co.name",        select: ["co.name", "count(inv.id) as invoices"]    } }  ]}
Example. Run it through check first: it validates the steps and prices them, and it is free.

Governance for Action1

Destructive actions wait for a yes.

21 Action1 actions are destructive. These are all of them:

  • Delete a useraction1.users.delete
  • Delete a managed endpointaction1.endpoints.delete
  • Delete a roleaction1.roles.delete
  • Delete an organizationaction1.organizations.delete
  • Delete a scheduled automationaction1.automations.schedules.delete
  • Delete a report subscriptionaction1.me.report_subscriptions.delete
  • Delete a CVE remediationaction1.vulnerabilities.remediations.delete
  • Stop a running automation instanceaction1.automations.instances.stop
  • Remove an action from a scheduled automationaction1.automations.schedules.actions.delete
  • Delete a library scriptaction1.scripts.delete
  • Delete a software repository packageaction1.packages.delete
  • Delete a settingaction1.settings.delete
  • Delete an agent deployeraction1.deployers.delete
  • Delete a data sourceaction1.data_sources.delete
  • Delete an endpoint groupaction1.endpoint_groups.delete
  • Request enterprise account closureaction1.enterprise.request_closure
  • Revoke an enterprise closure requestaction1.enterprise.revoke_closure
  • Remove a role from a useraction1.roles.users.delete
  • Delete a custom reportaction1.reports.custom.delete
  • Delete a package versionaction1.packages.versions.delete
  • Delete a package version's additional actionaction1.packages.versions.additional_actions.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.

doaction1.users.deleteconfirm_policy: human

Delete a user?

intent: the user asked me to delete a user

run suspended · waiting for a named person · key action1-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "action1-agent",  allowed_actions: ["action1.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "action1.users.delete", approver: "[email protected]" },    { match: "action1.endpoints.delete", approver: "[email protected]" },    { match: "action1.roles.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Action1 only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Action1 costs on actionlake.

Every Action1 action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Action1 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 135 Action1 actions
  • 135actions pageeach page of a long list is one call
  • 70reads 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 Action1 action.

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

Automations13
  • action1.automations.instances.createRun an automation nowwrite
  • action1.automations.instances.endpoint_results.detailsGet endpoint result details for an automation instanceread
  • action1.automations.instances.endpoint_results.listList an automation instance's endpoint resultsread
  • action1.automations.instances.getGet an automation instanceread
  • action1.automations.instances.listList automation instancesread
  • action1.automations.instances.stopStop a running automation instancedestructive
  • action1.automations.schedules.actions.deleteRemove an action from a scheduled automationdestructive
  • action1.automations.schedules.createCreate a scheduled automationwrite
  • action1.automations.schedules.deleteDelete a scheduled automationdestructive
  • action1.automations.schedules.deployment_statuses.listList a scheduled automation's deployment statusesread
  • action1.automations.schedules.getGet a scheduled automationread
  • action1.automations.schedules.listList scheduled automationsread
  • action1.automations.schedules.updateUpdate a scheduled automationwrite
Packages13
  • action1.packages.cloneClone a software repository packagewrite
  • action1.packages.createCreate a software repository packagewrite
  • action1.packages.deleteDelete a software repository packagedestructive
  • action1.packages.getGet a software repository packageread
  • action1.packages.listList software repository packagesread
  • action1.packages.match_conflicts.getGet a package's match conflictsread
  • action1.packages.match_conflicts.listList package match conflictsread
  • action1.packages.updateUpdate a software repository packagewrite
  • action1.packages.versions.additional_actions.deleteDelete a package version's additional actiondestructive
  • action1.packages.versions.createCreate a package versionwrite
  • action1.packages.versions.deleteDelete a package versiondestructive
  • action1.packages.versions.getGet a package versionread
  • action1.packages.versions.updateUpdate a package versionwrite
Endpoints11
  • action1.endpoints.agent_installation.getGet agent installation linkread
  • action1.endpoints.deleteDelete a managed endpointdestructive
  • action1.endpoints.getGet a managed endpointread
  • action1.endpoints.listList managed endpointsread
  • action1.endpoints.missing_updates.listList an endpoint's missing updatesread
  • action1.endpoints.moveMove an endpoint to another organizationwrite
  • action1.endpoints.remote_sessions.createStart a remote sessionwrite
  • action1.endpoints.remote_sessions.getGet a remote sessionread
  • action1.endpoints.remote_sessions.updateUpdate a remote sessionwrite
  • action1.endpoints.status.getGet endpoint status summaryread
  • action1.endpoints.updateUpdate a managed endpointwrite
Roles9
  • action1.roles.cloneClone a rolewrite
  • action1.roles.createCreate a rolewrite
  • action1.roles.deleteDelete a roledestructive
  • action1.roles.getGet a roleread
  • action1.roles.listList rolesread
  • action1.roles.updateUpdate a rolewrite
  • action1.roles.users.createAssign a role to a userwrite
  • action1.roles.users.deleteRemove a role from a userdestructive
  • action1.roles.users.listList users assigned a roleread
Endpoint groups7
  • action1.endpoint_groups.contents.listList endpoints in a groupread
  • action1.endpoint_groups.contents.updateAdd or remove endpoints in a groupwrite
  • action1.endpoint_groups.createCreate an endpoint groupwrite
  • action1.endpoint_groups.deleteDelete an endpoint groupdestructive
  • action1.endpoint_groups.getGet an endpoint groupread
  • action1.endpoint_groups.listList endpoint groupsread
  • action1.endpoint_groups.updateUpdate an endpoint groupwrite
Vulnerabilities7
  • action1.vulnerabilities.endpoints.listList endpoints affected by a CVEread
  • action1.vulnerabilities.getGet a vulnerabilityread
  • action1.vulnerabilities.listList vulnerabilitiesread
  • action1.vulnerabilities.remediations.createCreate a CVE remediationwrite
  • action1.vulnerabilities.remediations.deleteDelete a CVE remediationdestructive
  • action1.vulnerabilities.remediations.listList a CVE's remediationsread
  • action1.vulnerabilities.remediations.updateUpdate a CVE remediationwrite
Me6
  • action1.me.getGet the current API userread
  • action1.me.report_subscriptions.createCreate a report subscriptionwrite
  • action1.me.report_subscriptions.deleteDelete a report subscriptiondestructive
  • action1.me.report_subscriptions.listList my report subscriptionsread
  • action1.me.report_subscriptions.updateUpdate a report subscriptionwrite
  • action1.me.updateUpdate the current user's profilewrite
Subscription6
  • action1.subscription.getGet the enterprise subscriptionread
  • action1.subscription.quote.createRequest a subscription quotewrite
  • action1.subscription.trial.createRequest an enterprise trialwrite
  • action1.subscription.usage.getGet enterprise license usageread
  • action1.subscription.usage.organizations.getGet an organization's license usageread
  • action1.subscription.usage.organizations.listList license usage per organizationread
Users6
  • action1.users.createCreate a userwrite
  • action1.users.deleteDelete a userdestructive
  • action1.users.getGet a userread
  • action1.users.listList usersread
  • action1.users.roles.listList a user's rolesread
  • action1.users.updateUpdate a userwrite
Data sources5
  • action1.data_sources.createCreate a data sourcewrite
  • action1.data_sources.deleteDelete a data sourcedestructive
  • action1.data_sources.getGet a data sourceread
  • action1.data_sources.listList data sourcesread
  • action1.data_sources.updateUpdate a data sourcewrite
Installed software5
  • action1.installed_software.endpoint.listList installed software on an endpointread
  • action1.installed_software.endpoint.requeryRe-query installed software on an endpointwrite
  • action1.installed_software.errors.listList installed software collection errorsread
  • action1.installed_software.listList installed softwareread
  • action1.installed_software.requeryRe-query installed softwarewrite
Reports5
  • action1.reports.custom.createCreate a custom reportwrite
  • action1.reports.custom.deleteDelete a custom reportdestructive
  • action1.reports.custom.updateUpdate a custom reportwrite
  • action1.reports.getGet a report or report categoryread
  • action1.reports.listList reports and report categoriesread
Scripts5
  • action1.scripts.createCreate a library scriptwrite
  • action1.scripts.deleteDelete a library scriptdestructive
  • action1.scripts.getGet a library scriptread
  • action1.scripts.listList library scriptsread
  • action1.scripts.updateUpdate a library scriptwrite
Settings5
  • action1.settings.createCreate a settingwrite
  • action1.settings.deleteDelete a settingdestructive
  • action1.settings.getGet a settingread
  • action1.settings.listList settingsread
  • action1.settings.updateUpdate a settingwrite
Deployers4
  • action1.deployers.deleteDelete an agent deployerdestructive
  • action1.deployers.getGet an agent deployerread
  • action1.deployers.installation.getGet deployer installation linkread
  • action1.deployers.listList agent deployersread
Enterprise4
  • action1.enterprise.getGet the enterpriseread
  • action1.enterprise.request_closureRequest enterprise account closuredestructive
  • action1.enterprise.revoke_closureRevoke an enterprise closure requestdestructive
  • action1.enterprise.updateUpdate the enterprisewrite
Organizations4
  • action1.organizations.createCreate an organizationwrite
  • action1.organizations.deleteDelete an organizationdestructive
  • action1.organizations.listList organizationsread
  • action1.organizations.updateUpdate an organizationwrite
Report data4
  • action1.report_data.drilldown.listDrill down into a report rowread
  • action1.report_data.errors.listList report data collection errorsread
  • action1.report_data.listList report data rowsread
  • action1.report_data.requeryRe-query report datawrite
Updates4
  • action1.updates.approvals.updateApprove or decline updateswrite
  • action1.updates.endpoints.listList endpoints missing an update versionread
  • action1.updates.getList missing update versions for a packageread
  • action1.updates.listList missing updatesread
Action templates2
  • action1.action_templates.getGet an automation action templateread
  • action1.action_templates.listList automation action templatesread
Agent deployment2
  • action1.agent_deployment.getGet agent deployment settingsread
  • action1.agent_deployment.updateUpdate agent deployment settingswrite
Audit events2
  • action1.audit_events.getGet an audit trail eventread
  • action1.audit_events.listList audit trail eventsread
Setting templates2
  • action1.setting_templates.getGet a setting templateread
  • action1.setting_templates.listList setting templatesread
Cve descriptions1
  • action1.cve_descriptions.getGet a CVE descriptionread
Logs1
  • action1.logs.listList agent and system logsread
Permissions1
  • action1.permissions.listList permission templatesread
Search1
  • action1.search.querySearch endpoints, apps, updates and other objectsread

Questions

The Action1 MCP server, answered.

Is there an Action1 MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 135 Action1 actions across automations, packages, endpoints and roles, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Action1.

What do I need to connect Action1?

Action1 API Client ID (Configuration > API Credentials in the Action1 console) and Action1 API Client Secret, shown once when the API credential is created. Plus your host. The free call account { op: "connections.requirements", service: "action1" } lists exactly what to paste.

Can an AI agent delete or change things in Action1?

Only if its key allows it, and only with an explicit confirmation. 21 Action1 actions are destructive, including delete a user, delete a managed endpoint and delete a role. 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 Action1 API limit?

actionlake paces every call to the limits in the Action1 service file: 300 calls a minute per connection. Repeated reads are answered from cache (70 Action1 actions can be), which never reaches Action1.

What does an Action1 action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (135 Action1 actions page). Cache hits, searches, dry runs and calls Action1 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 Action1 API does it cover?

The Action1 API 3.0 (OpenAPI 3.1.0) at your Action1 instance's API base URL, which you enter when connecting (path /api/3.0). It is built from Action1's documentation as read on 23 October 2026. 135 actions in 27 areas, each one in the signed service file (version 1.0.0).

Can I combine Action1 with my other systems?

Yes. ask joins Action1 to NetSuite or HubSpot CRM on the same customer and returns the answer rather than every row. Action1 maps crm.company, which 227 other connectors also map.

Does actionlake keep my Action1 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 Action1 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 Action1 today.

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