---
title: "WithSecure Elements MCP server for AI agents - actionlake"
description: "Give Claude 64 WithSecure Elements actions through one MCP server: response actions, devices. Your agent never holds the credential. 100,000 calls a month free."
canonical: https://actionlake.com/connectors/withsecure-elements
updated: 2026-10-23
---

Connectors · MSP & PSA

# WithSecure Elements MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to WithSecure Elements and the rest of your systems. It gives your agent 64 WithSecure Elements actions (21 reads, 29 writes and 14 that wait for a confirmation) and holds the WithSecure Elements credential itself, so the agent never does. It paces WithSecure Elements's limits and records every call.

[Connect WithSecure Elements free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/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: "withsecure_elements.devices.list",
  intent: "check which WithSecure Elements account is connected"
}
# Query devices · read · 1 upstream call
```

- 64 actions in one signed file
- 21 read look, never change
- 29 write create and update
- 14 wait for a yes destructive, confirmed first

Set up

## Connect WithSecure Elements 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 WithSecure Elements.
   OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in. actionlake stores what you paste write-only, sealed under your tenant's key.
   - `client_id` WithSecure Elements API client ID
   - `client_secret` WithSecure Elements API client secret (shown once when the API client is created)
   ```
   account { op: "connections.requirements", service: "withsecure_elements" }
   # 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: "withsecure_elements.devices.list" }
   # query devices · read · 1 upstream call
   check { action: "withsecure_elements.api_keys.create", input: { … } }
   # free: inputs, permissions, cost and confirmations, nothing sent
   ```

WithSecure Elements at a glance

**Sign-in**

OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in.

**You provide**

`client_id` `client_secret`

**Limits we pace to**

300 calls a minute, per connection

**API covered**

WithSecure Elements API 1.0.0 (OpenAPI 3.0.3)`api.connect.withsecure.com`

**Built from**

WithSecure Elements's documentation, read 23 October 2026[connect.withsecure.com](https://connect.withsecure.com/specs/elements/rendered/api-spec.yaml) [connect.withsecure.com](https://connect.withsecure.com/api-reference/elements)

**Service file**

Version 1.0.0, signed (Ed25519)

**Cached reads**

17 of 21 reads, for up to 5 minutes; a write clears what it affects

**Shared entities**

4, so ask can line WithSecure Elements up with your other systems

**Data**

Processed and stored in Sydney, Australia. No US region yet

Capabilities

## What an AI agent can do in WithSecure Elements.

64 actions in 19 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

- **21** read look, never change
- **29** write create and update
- **14** destructive wait for a confirmation

1. ### Response actions
   34
   1 read · 23 write · 10 destructive
   Get status of response actions · Enumerate running processes · List scheduled tasks · Enumerate WMI persistence mechanisms
2. ### Devices
   4
   2 read · 1 write · 1 destructive
   Query devices · Update devices · Delete devices · Query devices (aggregations)
3. ### Invitations
   4
   1 read · 2 write · 1 destructive
   List invitations · Send new device invitations · Renew and resend invitations · Delete invitations
4. ### API keys
   3
   1 read · 1 write · 1 destructive
   List API keys · Create API key · Delete API key
5. ### Security events
   3
   3 read · 0 write · 0 destructive
   Read list of security events (deprecated) · Query security events (aggregations) · Query security events
6. ### Device operations
   2
   1 read · 0 write · 1 destructive
   List device operations · Trigger remote operations on devices
7. ### Incidents
   2
   1 read · 1 write · 0 destructive
   List BCDs (incidents) · Update status of BCDs
8. ### Audit logs
   1
   1 read · 0 write · 0 destructive
   List audit logs

**11 more areas · 11 actions**

- Databases **1**
- Exposure identities **1**
- Incident comments **1**
- Incident detections **1**
- Incident updates **1**
- Missing updates **1**
- Organizations **1**
- Profiles **1**
- Response action tasks **1**
- Software installations **1**
- Whoami **1**

Top actions

## The WithSecure Elements API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 18 of WithSecure Elements's 18 action names are shared with at least one other connector, so an agent learns them once.

| Action | What it does | Effect | Same name in |
| --- | --- | --- | --- |
| `withsecure_elements.devices.list` Query devices | Query devices. | read | `device.endpoint.list` 65 connectors |
| `withsecure_elements.security_events.list` Read list of security events (deprecated) | Read list of security events (deprecated). | read | `monitoring.alert.list` 51 connectors |
| `withsecure_elements.whoami.get` Get current user information | Get current user information. | read | `identity.current_user.get` 307 connectors |
| `withsecure_elements.api_keys.list` List API keys | List API keys. | read | `identity.api_key.list` 96 connectors |
| `withsecure_elements.incidents.list` List BCDs (incidents) | List BCDs (incidents). | read | `monitoring.incident.list` 19 connectors |
| `withsecure_elements.audit_logs.list` List audit logs | List audit logs. | read | `identity.audit_event.list` 51 connectors |
| `withsecure_elements.invitations.list` List invitations | List invitations. | read | `identity.invitation.list` 33 connectors |
| `withsecure_elements.api_keys.create` Create API key | Create API key. | write | `identity.api_key.create` 100 connectors |
| `withsecure_elements.invitations.create` Send new device invitations | Send new device invitations. | write | `identity.invitation.create` 41 connectors |
| `withsecure_elements.organizations.list` List organizations | List organizations. | read | `platform.tenant.list` 70 connectors |
| `withsecure_elements.devices.update` Update devices | Update devices. | write | `device.endpoint.update` 23 connectors |
| `withsecure_elements.devices.delete` Delete devices | Delete devices. | destructive | `device.endpoint.delete` 35 connectors |

Try it

## Prompts to paste into Claude.

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

1. Read read
   Which WithSecure Elements incidents are open, and how long has each been open?
   calls `withsecure_elements.incidents.list`
2. Write write
   Create API key in WithSecure Elements. Show me exactly what you will send before you save it.
   calls `withsecure_elements.api_keys.create`

Governance for WithSecure Elements

## Destructive actions wait for a yes.

14 WithSecure Elements actions are destructive. These are all of them:

- Delete devices `withsecure_elements.devices.delete`
- Delete API key `withsecure_elements.api_keys.delete`
- Delete invitations `withsecure_elements.invitations.delete`
- Execute response action (deprecated) `withsecure_elements.response_actions.create`
- Trigger remote operations on devices `withsecure_elements.device_operations.create`
- Reset Microsoft Entra password `withsecure_elements.response_actions.execute_reset_password`
- Delete registry key or value `withsecure_elements.response_actions.execute_delete_registry`
- Delete Windows service `withsecure_elements.response_actions.execute_delete_services`
- Terminate thread `withsecure_elements.response_actions.execute_terminate_thread`
- Block user access in Microsoft Entra `withsecure_elements.response_actions.execute_block_user_access`
- Terminate process `withsecure_elements.response_actions.execute_terminate_process`
- End Microsoft Entra session `withsecure_elements.response_actions.execute_end_current_session`
- Delete scheduled task `withsecure_elements.response_actions.execute_delete_scheduled_tasks`
- Delete WMI persistence objects `withsecure_elements.response_actions.execute_delete_wmi_persistence`

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.

do withsecure_elements.devices.delete confirm_policy: **human**

Delete devices?

**intent:** the user asked me to delete devices

run suspended · waiting for a named person · key _withsecure-elements-agent_ cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

```
account {
  op: "keys.create", name: "withsecure-elements-agent",
  allowed_actions: ["withsecure_elements.*"], cap_calls: 2000,
  confirm_policy: "human_for_writes",
  approval_rules: [
    { match: "withsecure_elements.devices.delete", approver: "lead@example.com" },
    { match: "withsecure_elements.api_keys.delete", approver: "lead@example.com" },
    { match: "withsecure_elements.invitations.delete", approver: "lead@example.com" }
  ]
}
```

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

Cost

## What WithSecure Elements costs on actionlake.

Every WithSecure Elements action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call WithSecure Elements 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.

- 1 upstream call per action all 64 WithSecure Elements actions
- 15 actions page each page of a long list is one call
- 17 reads can be cached a cache hit costs nothing
- 100,000 calls a month, free paid plans from US$49 a month for 250,000

[See pricing](https://actionlake.com/pricing)

Action index

## Every WithSecure Elements action.

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

**Response actions 34**

- `withsecure_elements.response_actions.create` Execute response action (deprecated) destructive
- `withsecure_elements.response_actions.execute_block_user_access` Block user access in Microsoft Entra destructive
- `withsecure_elements.response_actions.execute_delete_registry` Delete registry key or value destructive
- `withsecure_elements.response_actions.execute_delete_scheduled_tasks` Delete scheduled task destructive
- `withsecure_elements.response_actions.execute_delete_services` Delete Windows service destructive
- `withsecure_elements.response_actions.execute_delete_wmi_persistence` Delete WMI persistence objects destructive
- `withsecure_elements.response_actions.execute_end_current_session` End Microsoft Entra session destructive
- `withsecure_elements.response_actions.execute_enumerate_processes` Enumerate running processes write
- `withsecure_elements.response_actions.execute_enumerate_scheduled_tasks` List scheduled tasks write
- `withsecure_elements.response_actions.execute_enumerate_wmi_persistence` Enumerate WMI persistence mechanisms write
- `withsecure_elements.response_actions.execute_full_memory_dump` Create full memory dump write
- `withsecure_elements.response_actions.execute_map_file_system` List file system structure write
- `withsecure_elements.response_actions.execute_map_registry` List registry keys and values write
- `withsecure_elements.response_actions.execute_netstat` Retrieve network connections write
- `withsecure_elements.response_actions.execute_process_memory_dump` Retrieve process memory dump write
- `withsecure_elements.response_actions.execute_reset_password` Reset Microsoft Entra password destructive
- `withsecure_elements.response_actions.execute_retrieve_amcache` Retrieve amcache files write
- `withsecure_elements.response_actions.execute_retrieve_antivirus_logs` Retrieve antivirus logs write
- `withsecure_elements.response_actions.execute_retrieve_browser_artefacts` Retrieve browser artifacts write
- `withsecure_elements.response_actions.execute_retrieve_event_log_files` Retrieve Windows event log files write
- `withsecure_elements.response_actions.execute_retrieve_event_log_tracing` Retrieve event log tracing files write
- `withsecure_elements.response_actions.execute_retrieve_files` Retrieve files from device write
- `withsecure_elements.response_actions.execute_retrieve_jump_list` Retrieve jump list files write
- `withsecure_elements.response_actions.execute_retrieve_log_entries` Retrieve Windows event log entries write
- `withsecure_elements.response_actions.execute_retrieve_mbr` Retrieve master boot record write
- `withsecure_elements.response_actions.execute_retrieve_mft` Retrieve master file table write
- `withsecure_elements.response_actions.execute_retrieve_prefetch` Retrieve prefetch files write
- `withsecure_elements.response_actions.execute_retrieve_rdp_cache` Retrieve RDP cache files write
- `withsecure_elements.response_actions.execute_retrieve_recently_accessed` Retrieve recently accessed files write
- `withsecure_elements.response_actions.execute_retrieve_registry_hives` Retrieve registry hive files write
- `withsecure_elements.response_actions.execute_retrieve_srumdb` Retrieve SRUM database write
- `withsecure_elements.response_actions.execute_terminate_process` Terminate process destructive
- `withsecure_elements.response_actions.execute_terminate_thread` Terminate thread destructive
- `withsecure_elements.response_actions.list` Get status of response actions read

**Devices 4**

- `withsecure_elements.devices.aggregate` Query devices (aggregations) read
- `withsecure_elements.devices.delete` Delete devices destructive
- `withsecure_elements.devices.list` Query devices read
- `withsecure_elements.devices.update` Update devices write

**Invitations 4**

- `withsecure_elements.invitations.create` Send new device invitations write
- `withsecure_elements.invitations.delete` Delete invitations destructive
- `withsecure_elements.invitations.list` List invitations read
- `withsecure_elements.invitations.resend_or_renew` Renew and resend invitations write

**API keys 3**

- `withsecure_elements.api_keys.create` Create API key write
- `withsecure_elements.api_keys.delete` Delete API key destructive
- `withsecure_elements.api_keys.list` List API keys read

**Security events 3**

- `withsecure_elements.security_events.aggregate` Query security events (aggregations) read
- `withsecure_elements.security_events.list` Read list of security events (deprecated) read
- `withsecure_elements.security_events.query` Query security events read

**Device operations 2**

- `withsecure_elements.device_operations.create` Trigger remote operations on devices destructive
- `withsecure_elements.device_operations.list` List device operations read

**Incidents 2**

- `withsecure_elements.incidents.list` List BCDs (incidents) read
- `withsecure_elements.incidents.update` Update status of BCDs write

**Audit logs 1**

- `withsecure_elements.audit_logs.list` List audit logs read

**Databases 1**

- `withsecure_elements.databases.latest_versions` Get the latest version information for databases read

**Exposure identities 1**

- `withsecure_elements.exposure_identities.list` Query identities read

**Incident comments 1**

- `withsecure_elements.incident_comments.create` Add comment to BCDs write

**Incident detections 1**

- `withsecure_elements.incident_detections.list` List detections for given BCD in organization scope read

**Incident updates 1**

- `withsecure_elements.incident_updates.list` Get BCD update history read

**Missing updates 1**

- `withsecure_elements.missing_updates.list` Query missing software updates read

**Organizations 1**

- `withsecure_elements.organizations.list` List organizations read

**Profiles 1**

- `withsecure_elements.profiles.list` List profiles read

**Response action tasks 1**

- `withsecure_elements.response_action_tasks.list` Get response action tasks read

**Software installations 1**

- `withsecure_elements.software_installations.list` Count installed software updates read

**Whoami 1**

- `withsecure_elements.whoami.get` Get current user information read

Questions

## The WithSecure Elements MCP server, answered.

**Is there a WithSecure Elements MCP server for Claude?**

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 64 WithSecure Elements actions across response actions, devices, invitations and API keys, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by WithSecure Elements.

**What do I need to connect WithSecure Elements?**

WithSecure Elements API client ID and WithSecure Elements API client secret (shown once when the API client is created). The free call account { op: "connections.requirements", service: "withsecure_elements" } lists exactly what to paste.

**Can an AI agent delete or change things in WithSecure Elements?**

Only if its key allows it, and only with an explicit confirmation. 14 WithSecure Elements actions are destructive, including delete devices, delete API key and delete invitations. 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 WithSecure Elements API limit?**

actionlake paces every call to the limits in the WithSecure Elements service file: 300 calls a minute per connection. Repeated reads are answered from cache (17 WithSecure Elements actions can be), which never reaches WithSecure Elements.

**What does a WithSecure Elements action cost?**

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (15 WithSecure Elements actions page). Cache hits, searches, dry runs and calls WithSecure Elements 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 WithSecure Elements API does it cover?**

The WithSecure Elements API 1.0.0 (OpenAPI 3.0.3) at api.connect.withsecure.com. It is built from WithSecure Elements's documentation as read on 23 October 2026. 64 actions in 19 areas, each one in the signed service file (version 1.0.0).

**Does actionlake keep my WithSecure Elements 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 WithSecure Elements 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 WithSecure Elements

Shares the most action names with

- [Zabbix 8](https://actionlake.com/connectors/zabbix)
- [Automox 7](https://actionlake.com/connectors/automox)
- [Liongard 7](https://actionlake.com/connectors/liongard)
- [Tailscale 6](https://actionlake.com/connectors/tailscale)
- [Microsoft 365 Lighthouse and GDAP 4](https://actionlake.com/connectors/microsoft-365-lighthouse-and-gdap)
- [HPE Aruba Networking Central 3](https://actionlake.com/connectors/hpe-aruba-networking-central)

Joins with, on shared entities

- [Dynatrace 3](https://actionlake.com/connectors/dynatrace)
- [Rapid7 InsightIDR 3](https://actionlake.com/connectors/rapid7-insightidr)
- [Palo Alto Networks Cortex XDR 3](https://actionlake.com/connectors/palo-alto-networks-cortex-xdr)
- [Microsoft 365 Users 2](https://actionlake.com/connectors/microsoft-365-users)
- [CrowdStrike Falcon 2](https://actionlake.com/connectors/crowdstrike-falcon)
- [Rootly 2](https://actionlake.com/connectors/rootly)

Browse

- [All MSP & PSA connectors](https://actionlake.com/connectors/category/msp-and-psa)
- [All connectors](https://actionlake.com/connectors)
- [How actionlake compares](https://actionlake.com/compare)

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

## Give your agent WithSecure Elements today.

[Connect WithSecure Elements free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing)

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

---

Source: https://actionlake.com/connectors/withsecure-elements
More: https://actionlake.com/llms.txt