Connectors · MSP & PSA

Lansweeper MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Lansweeper and the rest of your systems. It gives your agent 50 Lansweeper actions (29 reads, 14 writes and 7 that wait for a confirmation) and holds the Lansweeper credential itself, so the agent never does. It paces Lansweeper's limits and records every call.

Connect Lansweeper free See 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

50actionsin one signed file
29readlook, never change
14writecreate and update
7wait for a yesdestructive, confirmed first

Set up

Connect Lansweeper in three steps.

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
02
Connect Lansweeper.
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_tokenLansweeper personal access token (PAT)
```
account { op: "connections.requirements", service: "lansweeper" }
# free: exactly what to paste, and what is found for you
```

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: "lansweeper.sites.list" }# list authorized sites · read · 1 upstream callcheck { action: "lansweeper.assets.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Lansweeper 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_token
Limits we pace to: 150 calls a minute, per connection
API covered: Lansweeper Data API v2 (GraphQL)api.lansweeper.com
Built from: Lansweeper's documentation, read 23 October 2026developer.lansweeper.com developer.lansweeper.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 29 of 29 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 2, so ask can line Lansweeper up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Lansweeper.

50 actions in 28 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

29readlook, never change
14writecreate and update
7destructivewait for a confirmation

Asset groups
6
1 read · 3 write · 2 destructive
Create asset group · List asset groups · Add assets to asset group · Rename asset group
Assets
6
2 read · 3 write · 1 destructive
List assets · Add asset · Get asset details · Edit asset
Ip locations
4
1 read · 2 write · 1 destructive
Create IP locations · List IP locations · Update IP locations · Delete IP locations
Webhooks
4
1 read · 2 write · 1 destructive
Create webhook · List webhooks · Edit webhook · Delete webhook
Exports
3
1 read · 1 write · 1 destructive
Export filtered assets · Get export status · Cancel export
Relations
2
0 read · 1 write · 1 destructive
Create relation · Delete relation
Report full exports
2
1 read · 1 write · 0 destructive
Start a full report export · Get full report export status
Sites
2
2 read · 0 write · 0 destructive
List authorized sites · Get site

20 more areas · 21 actions

Sources 2
Accounts 1
Affected assets 1
Asset software 1
Asset states 1
Asset types 1
Assets with software 1
Assets without software 1
Audit trails 1
KB patches 1
Me 1
Relation types 1
Report results 1
Report status 1
Reports 1
Scanning tasks 1
Software 1
Software details 1
Users 1
Vulnerabilities 1

Top actions

The Lansweeper API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 17 of Lansweeper's 17 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`lansweeper.me.get`Get the authenticated user	The user the token belongs to, with the site profiles it holds.	read	`identity.current_user.get`307 connectors
`lansweeper.accounts.list`List site accounts	Lansweeper accounts authorized on the site.	read	`identity.user.list`474 connectors
`lansweeper.assets.list`List assets	Asset inventory: one row per asset with the element paths requested in `fields`, paged and filterable.	read	`asset.asset.list`42 connectors
`lansweeper.assets.create`Add asset	Adds a manual asset to the site.	write	`asset.asset.create`27 connectors
`lansweeper.asset_types.list`List asset types	Asset types and their keys; the keys feed assetBasicInfo.typeKey.	read	`asset.asset_type.list`11 connectors
`lansweeper.webhooks.create`Create webhook	Creates a site webhook (at most 50 per site).	write	`automation.webhook.create`209 connectors
`lansweeper.webhooks.list`List webhooks	Webhooks created for the site.	read	`automation.webhook.list`202 connectors
`lansweeper.vulnerabilities.list`List vulnerabilities	CVEs (HIGH confidence) affecting the site.	read	`security.vulnerability.list`14 connectors
`lansweeper.audit_trails.list`List audit trails	Audit trail records of the site between two dates.	read	`security.audit_log.list`69 connectors
`lansweeper.reports.list`List authorized reports	Reports the API client may run.	read	`analytics.report.list`37 connectors
`lansweeper.relations.create`Create relation	Relates two assets, or a user and an asset.	write	`asset.asset_relationship.add`4 connectors
`lansweeper.relations.delete`Delete relation	Deletes a relation; returns its id.	destructive	`asset.asset_relationship.remove`4 connectors

Try it

Prompts to paste into Claude.

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

Readread
Who has access in Lansweeper? List every user and their role.
callslansweeper.accounts.list
Writewrite
Add asset in Lansweeper. Show me exactly what you will send before you save it.
callslansweeper.assets.create

Governance for Lansweeper

Destructive actions wait for a yes.

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

Delete assetslansweeper.assets.delete
Delete webhooklansweeper.webhooks.delete
Delete relationlansweeper.relations.delete
Delete asset grouplansweeper.asset_groups.delete
Delete IP locationslansweeper.ip_locations.delete
Remove assets from asset grouplansweeper.asset_groups.remove_assets
Cancel exportlansweeper.exports.cancel

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.

dolansweeper.assets.deleteconfirm_policy: human

Delete assets?

intent: the user asked me to delete assets

run suspended · waiting for a named person · key lansweeper-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "lansweeper-agent",  allowed_actions: ["lansweeper.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "lansweeper.assets.delete", approver: "[email protected]" },    { match: "lansweeper.webhooks.delete", approver: "[email protected]" },    { match: "lansweeper.relations.delete", approver: "[email protected]" }  ]}

Illustrative. Scoped to Lansweeper only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Lansweeper costs on actionlake.

Every Lansweeper action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Lansweeper 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 50 Lansweeper actions
50actions pageeach page of a long list is one call
29reads 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 Lansweeper action.

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

Asset groups6

lansweeper.asset_groups.add_assetsAdd assets to asset groupwrite
lansweeper.asset_groups.createCreate asset groupwrite
lansweeper.asset_groups.deleteDelete asset groupdestructive
lansweeper.asset_groups.listList asset groupsread
lansweeper.asset_groups.remove_assetsRemove assets from asset groupdestructive
lansweeper.asset_groups.updateRename asset groupwrite

Assets6

lansweeper.assets.bulk_updateEdit assets in bulkwrite
lansweeper.assets.createAdd assetwrite
lansweeper.assets.deleteDelete assetsdestructive
lansweeper.assets.getGet asset detailsread
lansweeper.assets.listList assetsread
lansweeper.assets.updateEdit assetwrite

Ip locations4

lansweeper.ip_locations.createCreate IP locationswrite
lansweeper.ip_locations.deleteDelete IP locationsdestructive
lansweeper.ip_locations.listList IP locationsread
lansweeper.ip_locations.updateUpdate IP locationswrite

Webhooks4

lansweeper.webhooks.createCreate webhookwrite
lansweeper.webhooks.deleteDelete webhookdestructive
lansweeper.webhooks.listList webhooksread
lansweeper.webhooks.updateEdit webhookwrite

Exports3

lansweeper.exports.cancelCancel exportdestructive
lansweeper.exports.createExport filtered assetswrite
lansweeper.exports.getGet export statusread

Relations2

lansweeper.relations.createCreate relationwrite
lansweeper.relations.deleteDelete relationdestructive

Report full exports2

lansweeper.report_full_exports.createStart a full report exportwrite
lansweeper.report_full_exports.getGet full report export statusread

Sites2

lansweeper.sites.getGet siteread
lansweeper.sites.listList authorized sitesread

Sources2

lansweeper.sources.listList discovery sourcesread
lansweeper.sources.scan_nowScan a discovery source nowwrite

Accounts1

lansweeper.accounts.listList site accountsread

Affected assets1

lansweeper.affected_assets.listList assets affected by a CVEread

Asset software1

lansweeper.asset_software.listList an asset's softwareread

Asset states1

lansweeper.asset_states.listList asset statesread

Asset types1

lansweeper.asset_types.listList asset typesread

Assets with software1

lansweeper.assets_with_software.listList assets with a software installedread

Assets without software1

lansweeper.assets_without_software.listList assets without a software installedread

Audit trails1

lansweeper.audit_trails.listList audit trailsread

KB patches1

lansweeper.kb_patches.listList KB patches for a CVEread

Me1

lansweeper.me.getGet the authenticated userread

Relation types1

lansweeper.relation_types.listList relation typesread

Report results1

lansweeper.report_results.getGet report results URLread

Report status1

lansweeper.report_status.getGet report execution statusread

Reports1

lansweeper.reports.listList authorized reportsread

Scanning tasks1

lansweeper.scanning_tasks.listList scanning tasksread

Software1

lansweeper.software.listList software across the siteread

Software details1

lansweeper.software_details.getGet software detailsread

Users1

lansweeper.users.listList usersread

Vulnerabilities1

lansweeper.vulnerabilities.listList vulnerabilitiesread

Questions

The Lansweeper MCP server, answered.

Is there a Lansweeper MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 50 Lansweeper actions across asset groups, assets, ip locations and webhooks, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Lansweeper.

What do I need to connect Lansweeper?

Lansweeper personal access token (PAT). The free call account { op: "connections.requirements", service: "lansweeper" } lists exactly what to paste.

Can an AI agent delete or change things in Lansweeper?

Only if its key allows it, and only with an explicit confirmation. 7 Lansweeper actions are destructive, including delete assets, delete webhook and delete relation. 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 Lansweeper API limit?

actionlake paces every call to the limits in the Lansweeper service file: 150 calls a minute per connection. Repeated reads are answered from cache (29 Lansweeper actions can be), which never reaches Lansweeper.

What does a Lansweeper action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (50 Lansweeper actions page). Cache hits, searches, dry runs and calls Lansweeper 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 Lansweeper API does it cover?

The Lansweeper Data API v2 (GraphQL) at api.lansweeper.com. It is built from Lansweeper's documentation as read on 23 October 2026. 50 actions in 28 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Lansweeper 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 Lansweeper 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 Lansweeper today.

Connect Lansweeper free See pricing

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

Lansweeper MCP server for AI agents.

Connect Lansweeper in three steps.

Add actionlake to Claude.

Connect Lansweeper.

Make the first call. Check before a write.

What an AI agent can do in Lansweeper.

Asset groups

Assets

Ip locations

Webhooks

Exports

Relations

Report full exports

Sites