Skip to content
actionlake
Start free

Connectors · MSP & PSA

Liongard MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Liongard and the rest of your systems. It gives your agent 96 Liongard actions (56 reads, 29 writes and 11 that wait for a confirmation) and holds the Liongard credential itself, so the agent never does. It paces Liongard's limits and records every call.

Connect Liongard freeSee pricing

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: "liongard.users.list",  intent: "check which Liongard account is connected"}# List users · read · 1 upstream call
  • 96actionsin one signed file
  • 56readlook, never change
  • 29writecreate and update
  • 11wait for a yesdestructive, confirmed first

Set up

Connect Liongard 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 Liongard.

    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.

    • access_key_idLiongard Access Key ID: in Liongard open the profile menu > Account Settings > Access Tokens > Generate New Token
    • access_key_secretLiongard Access Key Secret, shown once beside the Access Key ID when the token is generated
    • hostWhere your Liongard lives: your host
    account { op: "connections.requirements", service: "liongard" }
# 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: "liongard.users.list" }# list users · read · 1 upstream callcheck { action: "liongard.users.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Liongard 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
access_key_idaccess_key_secret
Setup fields
host
Limits we pace to
100 calls a minute, per connection
API covered
Liongard REST API v1 and v2 (OpenAPI 3.0.3 definitions embedded in docs.liongard.com), at your Liongard instance's API base URL, which you enter when connecting (path /api)
Built from
Liongard's documentation, read 23 October 2026docs.liongard.comdocs.liongard.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
56 of 56 reads, for up to 5 minutes; a write clears what it affects
Shared entities
4, so ask can line Liongard up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Liongard.

96 actions in 21 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 56readlook, never change
  • 29writecreate and update
  • 11destructivewait for a confirmation

  1. Environments V2

    10

    5 read · 4 write · 1 destructive

    List environments (v2) · Count environments (v2) · Get an environment (v2) · Get an environment's related entities (v2)

  2. Launchpoints

    10

    3 read · 5 write · 2 destructive

    List launchpoints · Count launchpoints · Get a launchpoint · Create a launchpoint

  3. Agents

    9

    4 read · 3 write · 2 destructive

    List agents · Get an agent · Update an agent · Delete an agent

  4. Environments

    8

    4 read · 3 write · 1 destructive

    List environments · Get an environment · Create an environment · Update an environment

  5. Metrics

    6

    3 read · 2 write · 1 destructive

    List metrics · Evaluate metrics for up to 10 systems · Create a metric · Evaluate metrics for systems, optionally at a past date

  6. Users

    6

    3 read · 2 write · 1 destructive

    List users · Get a user · Create a user · Update a user

  7. Webhooks

    6

    2 read · 3 write · 1 destructive

    List webhooks (v2) · Get a webhook (v2) · Create a webhook (v2) · Update a webhook (v2)

  8. Access keys

    4

    2 read · 1 write · 1 destructive

    List access keys · Create an access key · Delete an access key · Count access keys

13 more areas · 37 actions
  • Detections 4
  • Environment groups 4
  • Inventory devices 4
  • Inventory identities 4
  • Metrics V2 4
  • Timeline 4
  • Alerts 3
  • Inspectors 3
  • Systems 3
  • Dataprints 1
  • Groups 1
  • Launchpoint logs 1
  • Timelines 1

Top actions

The Liongard API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 30 of Liongard's 31 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
liongard.users.listList usersReturns a list of users in your Liongard Instance.readidentity.user.list474 connectors
liongard.environments.listList environmentsFetch all environments in your Service Provider.readcrm.company.list162 connectors
liongard.users.getGet a userReturns a Single User.readidentity.user.get399 connectors
liongard.users.createCreate a userWhen creating and using the Manger or Reader Roles it is required to use either the Environment/EnvironmentID or EnvironmentGroupID/EnvironmentGroup to select…writeidentity.user.create262 connectors
liongard.agents.listList agentsList all agents.readdevice.endpoint.list65 connectors
liongard.alerts.listList alertsReturns a list of alerts that have been raised.readmonitoring.alert.list51 connectors
liongard.groups.listList assignable user groups (roles)Returns a List of available Assignable Roles for a user.readidentity.role.list184 connectors
liongard.users.updateUpdate a userUpdates a single User.writeidentity.user.update280 connectors
liongard.environments.getGet an environmentGet a single environment.readcrm.company.get162 connectors
liongard.users.deleteDelete a userRemove a single User.destructiveidentity.user.delete253 connectors
liongard.access_keys.listList access keysReturns a List of Access Tokens created by user.readidentity.api_key.list96 connectors
liongard.access_keys.createCreate an access keyCreate an Access Token with the permission of user or with only 'Add Agent' permission.writeidentity.api_key.create100 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

    Which Liongard alerts are open right now? Group them by service.

    callsliongard.alerts.list

  2. Writewrite

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

    callsliongard.users.create

  3. Across systemsread

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

    callsliongard.environments.listnetsuite.views.invoices

Across your systems

Liongard, joined to the rest of your business.

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

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

    liongard.environments.list + netsuite.views.invoices, on crm.company · NetSuite

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

    liongard.environments.list + hubspot_crm.tickets.list, on crm.company · HubSpot CRM

Also mapped by other connectorsidentity.user 517crm.company 227device.endpoint 69monitoring.alert 56
ask
ask {  intent: "which Liongard companies have invoices in NetSuite, and how many each",  steps: [    { action: "liongard.environments.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 Liongard

Destructive actions wait for a yes.

11 Liongard actions are destructive. These are all of them:

  • Delete a userliongard.users.delete
  • Delete an environmentliongard.environments.delete
  • Delete an access keyliongard.access_keys.delete
  • Delete an agentliongard.agents.delete
  • Delete a webhook (v2)liongard.webhooks.delete
  • Delete a custom metricliongard.metrics.delete
  • Delete many agents (v2)liongard.agents.delete_bulk
  • Delete a launchpointliongard.launchpoints.delete
  • Delete an environment (v2)liongard.environments_v2.delete
  • Delete many launchpointsliongard.launchpoints.delete_bulk
  • Delete environment groups (v2)liongard.environment_groups.delete_bulk

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.

doliongard.users.deleteconfirm_policy: human

Delete a user?

intent: the user asked me to delete a user

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

Cost

What Liongard costs on actionlake.

Every Liongard action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Liongard 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 96 Liongard actions
  • 96actions pageeach page of a long list is one call
  • 56reads 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 Liongard action.

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

Environments V210
  • liongard.environments_v2.countCount environments (v2)read
  • liongard.environments_v2.createCreate an environment (v2)write
  • liongard.environments_v2.create_bulkCreate environments in bulk (v2)write
  • liongard.environments_v2.dashboard_queryRun environment dashboard queries (v2)read
  • liongard.environments_v2.deleteDelete an environment (v2)destructive
  • liongard.environments_v2.getGet an environment (v2)read
  • liongard.environments_v2.listList environments (v2)read
  • liongard.environments_v2.related_entitiesGet an environment's related entities (v2)read
  • liongard.environments_v2.updateUpdate an environment (v2)write
  • liongard.environments_v2.update_bulkUpdate environments in bulk (v2)write
Launchpoints10
  • liongard.launchpoints.countCount launchpointsread
  • liongard.launchpoints.createCreate a launchpointwrite
  • liongard.launchpoints.deleteDelete a launchpointdestructive
  • liongard.launchpoints.delete_bulkDelete many launchpointsdestructive
  • liongard.launchpoints.getGet a launchpointread
  • liongard.launchpoints.listList launchpointsread
  • liongard.launchpoints.runRun a launchpoint's inspection nowwrite
  • liongard.launchpoints.run_bulkRun inspections for many launchpointswrite
  • liongard.launchpoints.updateUpdate a launchpointwrite
  • liongard.launchpoints.update_bulkUpdate the schedule of many launchpointswrite
Agents9
  • liongard.agents.countCount agentsread
  • liongard.agents.create_installerGenerate a dynamic agent installer (v2)write
  • liongard.agents.deleteDelete an agentdestructive
  • liongard.agents.delete_bulkDelete many agents (v2)destructive
  • liongard.agents.flush_job_queueFlush an agent's job queuewrite
  • liongard.agents.getGet an agentread
  • liongard.agents.listList agentsread
  • liongard.agents.queryQuery agents with filters (v2)read
  • liongard.agents.updateUpdate an agentwrite
Environments8
  • liongard.environments.countCount environmentsread
  • liongard.environments.createCreate an environmentwrite
  • liongard.environments.create_bulkCreate environments in bulkwrite
  • liongard.environments.deleteDelete an environmentdestructive
  • liongard.environments.getGet an environmentread
  • liongard.environments.listList environmentsread
  • liongard.environments.related_entitiesGet an environment's related entitiesread
  • liongard.environments.updateUpdate an environmentwrite
Metrics6
  • liongard.metrics.createCreate a metricwrite
  • liongard.metrics.deleteDelete a custom metricdestructive
  • liongard.metrics.evaluate_bulkEvaluate metrics for up to 10 systemsread
  • liongard.metrics.evaluate_bulk_atEvaluate metrics for systems, optionally at a past dateread
  • liongard.metrics.listList metricsread
  • liongard.metrics.updateUpdate a metricwrite
Users6
  • liongard.users.countCount usersread
  • liongard.users.createCreate a userwrite
  • liongard.users.deleteDelete a userdestructive
  • liongard.users.getGet a userread
  • liongard.users.listList usersread
  • liongard.users.updateUpdate a userwrite
Webhooks6
  • liongard.webhooks.createCreate a webhook (v2)write
  • liongard.webhooks.create_signing_keyGenerate the webhook signing key (v2)write
  • liongard.webhooks.deleteDelete a webhook (v2)destructive
  • liongard.webhooks.getGet a webhook (v2)read
  • liongard.webhooks.listList webhooks (v2)read
  • liongard.webhooks.updateUpdate a webhook (v2)write
Access keys4
  • liongard.access_keys.countCount access keysread
  • liongard.access_keys.createCreate an access keywrite
  • liongard.access_keys.deleteDelete an access keydestructive
  • liongard.access_keys.listList access keysread
Detections4
  • liongard.detections.countCount detectionsread
  • liongard.detections.getGet a detectionread
  • liongard.detections.listList detectionsread
  • liongard.detections.queryQuery detections with filters (v2)read
Environment groups4
  • liongard.environment_groups.createCreate an environment group (v2)write
  • liongard.environment_groups.delete_bulkDelete environment groups (v2)destructive
  • liongard.environment_groups.listList environment groups (v2)read
  • liongard.environment_groups.updateUpdate an environment group (v2)write
Inventory devices4
  • liongard.inventory_devices.getGet an inventory device (v2)read
  • liongard.inventory_devices.queryQuery inventory devices (v2)read
  • liongard.inventory_devices.updateUpdate an inventory device's properties (v2)write
  • liongard.inventory_devices.update_bulkUpdate many inventory devices (v2)write
Inventory identities4
  • liongard.inventory_identities.getGet an inventory identity (v2)read
  • liongard.inventory_identities.queryQuery inventory identities (v2)read
  • liongard.inventory_identities.updateUpdate an inventory identity (v2)write
  • liongard.inventory_identities.update_bulkUpdate many inventory identities (v2)write
Metrics V24
  • liongard.metrics_v2.evaluateGet metric values for all systems (v2)read
  • liongard.metrics_v2.evaluate_systemsGet all enabled metric values for systems (v2)read
  • liongard.metrics_v2.listList metrics (v2)read
  • liongard.metrics_v2.related_environmentsList a metric's related environments (v2)read
Timeline4
  • liongard.timeline.countCount timeline entriesread
  • liongard.timeline.detailGet a timeline entry's raw detail (dataprint)read
  • liongard.timeline.getGet a timeline entryread
  • liongard.timeline.listList timeline entriesread
Alerts3
  • liongard.alerts.countCount alertsread
  • liongard.alerts.getGet an alertread
  • liongard.alerts.listList alertsread
Inspectors3
  • liongard.inspectors.listList inspector typesread
  • liongard.inspectors.templatesList an inspector's configuration templatesread
  • liongard.inspectors.versionsList an inspector's versionsread
Systems3
  • liongard.systems.countCount systemsread
  • liongard.systems.detail_viewGet a system's latest raw inspection dataread
  • liongard.systems.listList systemsread
Dataprints1
  • liongard.dataprints.evaluateEvaluate a JMESPath expression against a system's dataprint (v2)read
Groups1
  • liongard.groups.listList assignable user groups (roles)read
Launchpoint logs1
  • liongard.launchpoint_logs.getGet the log of one inspectionread
Timelines1
  • liongard.timelines.queryQuery timeline entries (v2)read

Questions

The Liongard MCP server, answered.

Is there a Liongard MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 96 Liongard actions across environments V2, launchpoints, agents and environments, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Liongard.

What do I need to connect Liongard?

Liongard Access Key ID: in Liongard open the profile menu > Account Settings > Access Tokens > Generate New Token and Liongard Access Key Secret, shown once beside the Access Key ID when the token is generated. Plus your host. The free call account { op: "connections.requirements", service: "liongard" } lists exactly what to paste.

Can an AI agent delete or change things in Liongard?

Only if its key allows it, and only with an explicit confirmation. 11 Liongard actions are destructive, including delete a user, delete an environment and delete an access key. 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 Liongard API limit?

actionlake paces every call to the limits in the Liongard service file: 100 calls a minute per connection. Repeated reads are answered from cache (56 Liongard actions can be), which never reaches Liongard.

What does a Liongard action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (96 Liongard actions page). Cache hits, searches, dry runs and calls Liongard 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 Liongard API does it cover?

The Liongard REST API v1 and v2 (OpenAPI 3.0.3 definitions embedded in docs.liongard.com) at your Liongard instance's API base URL, which you enter when connecting (path /api). It is built from Liongard's documentation as read on 23 October 2026. 96 actions in 21 areas, each one in the signed service file (version 1.0.0).

Can I combine Liongard with my other systems?

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

Does actionlake keep my Liongard 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 Liongard 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.

More connectors like Liongard

Shares the most action names with

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by Liongard; the name is the vendor's own. Counts are from the Liongard service file, version 1.0.0.

Give your agent Liongard today.

Connect Liongard freeSee pricing

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