---
title: "Torq MCP server for AI agents - actionlake"
description: "Give Claude 118 Torq actions through one MCP server: workflows, cases, secrets. Your agent never holds the credential. 100,000 calls a month free."
canonical: https://actionlake.com/connectors/torq
updated: 2026-10-23
---

Connectors · Identity & security

# Torq MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Torq and the rest of your systems. It gives your agent 118 Torq actions (56 reads, 46 writes and 16 that wait for a confirmation) and holds the Torq credential itself, so the agent never does. It paces Torq's limits and records every call.

[Connect Torq 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: "torq.users.list",
  intent: "check which Torq account is connected"
}
# List Users · read · 1 upstream call
```

- 118 actions in one signed file
- 56 read look, never change
- 46 write create and update
- 16 wait for a yes destructive, confirmed first

Set up

## Connect Torq 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 Torq.
   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` Torq API key Client ID
   - `client_secret` Torq API key Client Secret (shown once when the key is created)
   - `tenant_host` Where your Torq lives: your tenant host
   ```
   account { op: "connections.requirements", service: "torq" }
   # 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: "torq.users.list" }
   # list users · read · 1 upstream call
   check { action: "torq.roles.create", input: { … } }
   # free: inputs, permissions, cost and confirmations, nothing sent
   ```

Torq 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`

**Setup fields**

`tenant_host`

**Limits we pace to**

50 calls a second, per connection

**API covered**

Torq public REST API (v1alpha + v1 triage)`auth.torq.io/public`

**Built from**

Torq's documentation, read 23 October 2026[developers.torq.io](https://developers.torq.io/apidocs/overview) [developers.torq.io](https://developers.torq.io/llms.txt)

**Service file**

Version 1.0.0, signed (Ed25519)

**Cached reads**

51 of 56 reads, for up to 5 minutes; a write clears what it affects

**Shared entities**

2, so ask can line Torq up with your other systems

**Data**

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

Capabilities

## What an AI agent can do in Torq.

118 actions in 34 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

- **56** read look, never change
- **46** write create and update
- **16** destructive wait for a confirmation

1. ### Workflows
   13
   5 read · 6 write · 2 destructive
   List workflows · Retrieve a workflow · Update a workflow · Delete a workflow
2. ### Cases
   10
   4 read · 4 write · 2 destructive
   Query cases · Create a case · Retrieve a case · Update a case
3. ### Secrets
   6
   2 read · 3 write · 1 destructive
   List secrets · Create a secret · Retrieve a secret · Update a secret
4. ### Triage alerts
   6
   3 read · 3 write · 0 destructive
   List alerts · Retrieve alert · List alert history · Change verdict
5. ### Workspace variables
   6
   2 read · 3 write · 1 destructive
   Create a workspace variable · List workspace variables · Retrieve a workspace variable · Remove workspace variable sharing
6. ### Case links
   5
   2 read · 2 write · 1 destructive
   Link cases · List the case links · List link relations · Update a link
7. ### Case notes
   5
   2 read · 2 write · 1 destructive
   List the case notes · Add a note to a case · Retrieve a note · Update a note
8. ### Roles
   5
   2 read · 2 write · 1 destructive
   List roles · Create a role · Retrieve a role · Update a role

**26 more areas · 62 actions**

- SSO claim mappings **5**
- Step runners **5**
- Triage guidance **5**
- Case custom fields **4**
- Observables **4**
- Share requests **4**
- Users **4**
- Case observables **3**
- Case timeline **3**
- Runbooks **3**
- Workspaces **3**
- Executions **2**
- Integrations **2**
- Security settings **2**
- Triage verdict actions **2**
- Activity logs **1**
- API keys **1**
- Audit logs **1**
- Case assignees **1**
- Case attachments **1**
- Case categories **1**
- Case events **1**
- Case resolution reasons **1**
- Case reviewers **1**
- Case tags **1**
- Workflow tags **1**

Top actions

## The Torq API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 33 of Torq's 33 action names are shared with at least one other connector, so an agent learns them once.

| Action | What it does | Effect | Same name in |
| --- | --- | --- | --- |
| `torq.users.list` List Users | List Users. | read | `identity.user.list` 474 connectors |
| `torq.roles.list` List roles | List roles. | read | `identity.role.list` 184 connectors |
| `torq.roles.create` Create a role | Create a role. | write | `identity.role.create` 105 connectors |
| `torq.users.delete` Delete a user | Delete a user. | destructive | `identity.user.delete` 253 connectors |
| `torq.roles.update` Update a role | Update a role. | write | `identity.role.update` 98 connectors |
| `torq.audit_logs.list` List audit logs | List audit logs. | read | `security.audit_log.list` 69 connectors |
| `torq.api_keys.list` List API keys | List API keys. | read | `identity.api_key.list` 96 connectors |
| `torq.triage_alerts.query` List alerts | List alerts. | read | `security.alert.list` 22 connectors |
| `torq.secrets.list` List secrets | List secrets. | read | `security.secret.list` 21 connectors |
| `torq.secrets.create` Create a secret | Create a secret. | write | `security.secret.create` 19 connectors |
| `torq.cases.query` Query cases | Query cases. | read | `security.incident.list` 17 connectors |
| `torq.case_notes.list` List the case notes | List the case notes. | read | `security.incident_note.list` 9 connectors |

Try it

## Prompts to paste into Claude.

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

1. Read read
   Who has access in Torq? List every user and their role.
   calls `torq.users.list`
2. Write write
   Create a role in Torq. Show me exactly what you will send before you save it.
   calls `torq.roles.create`

Governance for Torq

## Destructive actions wait for a yes.

16 Torq actions are destructive. These are all of them:

- Delete a user `torq.users.delete`
- Delete a role `torq.roles.delete`
- Delete a secret `torq.secrets.delete`
- Delete a note `torq.case_notes.delete`
- Delete a case `torq.cases.delete`
- Delete a workflow `torq.workflows.delete`
- Unlink cases `torq.case_links.delete`
- Remove a tag from a case `torq.cases.remove_tags`
- Delete a step runner `torq.step_runners.delete`
- Remove a tag `torq.workflows.remove_tag`
- Deactivate a workspace `torq.workspaces.deactivate`
- Delete guidance `torq.triage_guidance.delete`
- Remove a custom field from a case `torq.case_custom_fields.remove`
- Delete a claim mapping `torq.sso_claim_mappings.delete`
- Delete a workspace variable `torq.workspace_variables.delete`
- Disassociate an observable from a case `torq.case_observables.disassociate`

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 torq.users.delete confirm_policy: **human**

Delete a user?

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

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

In the console, or from an emailed signed link.

a key for this connector

```
account {
  op: "keys.create", name: "torq-agent",
  allowed_actions: ["torq.*"], cap_calls: 2000,
  confirm_policy: "human_for_writes",
  approval_rules: [
    { match: "torq.users.delete", approver: "lead@example.com" },
    { match: "torq.roles.delete", approver: "lead@example.com" },
    { match: "torq.secrets.delete", approver: "lead@example.com" }
  ]
}
```

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

Cost

## What Torq costs on actionlake.

Every Torq action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Torq 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 118 Torq actions
- 118 actions page each page of a long list is one call
- 51 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 Torq action.

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

**Workflows 13**

- `torq.workflows.add_tag` Add a tag write
- `torq.workflows.delete` Delete a workflow destructive
- `torq.workflows.get` Retrieve a workflow read
- `torq.workflows.get_revision` Retrieve a revision read
- `torq.workflows.import` Import a workflow write
- `torq.workflows.list` List workflows read
- `torq.workflows.list_parents` List parent workflows read
- `torq.workflows.list_tags` List workflow tags read
- `torq.workflows.publish` Publish a workflow write
- `torq.workflows.remove_sharing` Remove workflow sharing write
- `torq.workflows.remove_tag` Remove a tag destructive
- `torq.workflows.unpublish` Unpublish a workflow write
- `torq.workflows.update` Update a workflow write

**Cases 10**

- `torq.cases.add_tags` Add a tag to a case write
- `torq.cases.bulk_create` Bulk create extended cases write
- `torq.cases.create` Create a case write
- `torq.cases.delete` Delete a case destructive
- `torq.cases.get` Retrieve a case read
- `torq.cases.get_bulk_create_operation` Retrieve bulk case creation state read
- `torq.cases.list_bulk_create_operations` List bulk case creation state read
- `torq.cases.query` Query cases read
- `torq.cases.remove_tags` Remove a tag from a case destructive
- `torq.cases.update` Update a case write

**Secrets 6**

- `torq.secrets.create` Create a secret write
- `torq.secrets.delete` Delete a secret destructive
- `torq.secrets.get` Retrieve a secret read
- `torq.secrets.list` List secrets read
- `torq.secrets.remove_sharing` Remove secret sharing write
- `torq.secrets.update` Update a secret write

**Triage alerts 6**

- `torq.triage_alerts.change_verdict` Change verdict write
- `torq.triage_alerts.confirm_verdict` Confirm verdict write
- `torq.triage_alerts.get` Retrieve alert read
- `torq.triage_alerts.list_history` List alert history read
- `torq.triage_alerts.query` List alerts read
- `torq.triage_alerts.undo_verdict_review` Undo verdict review write

**Workspace variables 6**

- `torq.workspace_variables.create` Create a workspace variable write
- `torq.workspace_variables.delete` Delete a workspace variable destructive
- `torq.workspace_variables.get` Retrieve a workspace variable read
- `torq.workspace_variables.list` List workspace variables read
- `torq.workspace_variables.remove_sharing` Remove workspace variable sharing write
- `torq.workspace_variables.update` Update a workspace variable write

**Case links 5**

- `torq.case_links.create` Link cases write
- `torq.case_links.delete` Unlink cases destructive
- `torq.case_links.list` List the case links read
- `torq.case_links.list_relations` List link relations read
- `torq.case_links.update` Update a link write

**Case notes 5**

- `torq.case_notes.create` Add a note to a case write
- `torq.case_notes.delete` Delete a note destructive
- `torq.case_notes.get` Retrieve a note read
- `torq.case_notes.list` List the case notes read
- `torq.case_notes.update` Update a note write

**Roles 5**

- `torq.roles.create` Create a role write
- `torq.roles.delete` Delete a role destructive
- `torq.roles.get` Retrieve a role read
- `torq.roles.list` List roles read
- `torq.roles.update` Update a role write

**SSO claim mappings 5**

- `torq.sso_claim_mappings.create` Add a claim mapping write
- `torq.sso_claim_mappings.delete` Delete a claim mapping destructive
- `torq.sso_claim_mappings.get` Retrieve a claim mapping read
- `torq.sso_claim_mappings.list` List claim mappings read
- `torq.sso_claim_mappings.update` Update a claim mapping write

**Step runners 5**

- `torq.step_runners.create` Create a step runner write
- `torq.step_runners.delete` Delete a step runner destructive
- `torq.step_runners.get` Retrieve a step runner read
- `torq.step_runners.list` List step runners read
- `torq.step_runners.regenerate_install_command` Regenerate a step runner install command write

**Triage guidance 5**

- `torq.triage_guidance.create` Create guidance write
- `torq.triage_guidance.delete` Delete guidance destructive
- `torq.triage_guidance.get` Retrieve guidance read
- `torq.triage_guidance.list` List guidance read
- `torq.triage_guidance.update` Update guidance write

**Case custom fields 4**

- `torq.case_custom_fields.add` Add a custom field to a case write
- `torq.case_custom_fields.list` List custom fields for cases read
- `torq.case_custom_fields.remove` Remove a custom field from a case destructive
- `torq.case_custom_fields.set` Update the value of a custom field write

**Observables 4**

- `torq.observables.create` Create an observable write
- `torq.observables.get` Retrieve an observable read
- `torq.observables.query` Query observables read
- `torq.observables.update` Update an observable write

**Share requests 4**

- `torq.share_requests.accept` Accept a share request write
- `torq.share_requests.create` Create a share request write
- `torq.share_requests.deny` Deny a share request write
- `torq.share_requests.list` List share requests read

**Users 4**

- `torq.users.delete` Delete a user destructive
- `torq.users.invite` Invite a new user write
- `torq.users.list` List Users read
- `torq.users.list_roles` List roles read

**Case observables 3**

- `torq.case_observables.associate` Associate an observable with a case write
- `torq.case_observables.disassociate` Disassociate an observable from a case destructive
- `torq.case_observables.list` List the case observables read

**Case timeline 3**

- `torq.case_timeline.add_comment` Add a timeline comment write
- `torq.case_timeline.attach_events` Add a timeline event write
- `torq.case_timeline.query` Query the case timeline read

**Runbooks 3**

- `torq.runbooks.get` Retrieve a runbook by ID read
- `torq.runbooks.get_by_name` Retrieve a runbook by name read
- `torq.runbooks.list` List runbooks read

**Workspaces 3**

- `torq.workspaces.create` Create a workspace write
- `torq.workspaces.deactivate` Deactivate a workspace destructive
- `torq.workspaces.list` List workspaces read

**Executions 2**

- `torq.executions.get` Retrieve an execution read
- `torq.executions.get_trigger_event` Retrieve a trigger event read

**Integrations 2**

- `torq.integrations.list` List integrations read
- `torq.integrations.remove_sharing` Remove integration sharing write

**Security settings 2**

- `torq.security_settings.get` Retrieve security settings read
- `torq.security_settings.set` Set security settings write

**Triage verdict actions 2**

- `torq.triage_verdict_actions.get` Retrieve verdict actions read
- `torq.triage_verdict_actions.update` Update verdict actions write

**Activity logs 1**

- `torq.activity_logs.list` List activity logs read

**API keys 1**

- `torq.api_keys.list` List API keys read

**Audit logs 1**

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

**Case assignees 1**

- `torq.case_assignees.list` List cases assignees read

**Case attachments 1**

- `torq.case_attachments.list` List the case attachments read

**Case categories 1**

- `torq.case_categories.list` List cases categories read

**Case events 1**

- `torq.case_events.query` List the case events read

**Case resolution reasons 1**

- `torq.case_resolution_reasons.list` List cases resolution reasons read

**Case reviewers 1**

- `torq.case_reviewers.list` List case reviewers read

**Case tags 1**

- `torq.case_tags.list` List cases tags read

**Workflow tags 1**

- `torq.workflow_tags.list` List tags read

Questions

## The Torq MCP server, answered.

**Is there a Torq MCP server for Claude?**

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 118 Torq actions across workflows, cases, secrets and triage alerts, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Torq.

**What do I need to connect Torq?**

Torq API key Client ID and Torq API key Client Secret (shown once when the key is created). Plus your tenant host. The free call account { op: "connections.requirements", service: "torq" } lists exactly what to paste.

**Can an AI agent delete or change things in Torq?**

Only if its key allows it, and only with an explicit confirmation. 16 Torq actions are destructive, including delete a user, delete a role and delete a secret. 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 Torq API limit?**

actionlake paces every call to the limits in the Torq service file: 50 calls a second per connection. Repeated reads are answered from cache (51 Torq actions can be), which never reaches Torq.

**What does a Torq action cost?**

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (118 Torq actions page). Cache hits, searches, dry runs and calls Torq 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 Torq API does it cover?**

The Torq public REST API (v1alpha + v1 triage) at auth.torq.io/public by default, or the base URL set when you connect. It is built from Torq's documentation as read on 23 October 2026. 118 actions in 34 areas, each one in the signed service file (version 1.0.0).

**Does actionlake keep my Torq 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 Torq 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 Torq

Shares the most action names with

- [Splunk SOAR 22](https://actionlake.com/connectors/splunk-soar)
- [Sekoia.io 22](https://actionlake.com/connectors/sekoia-io)
- [Trend Vision One 15](https://actionlake.com/connectors/trend-vision-one)
- [StrangeBee TheHive 14](https://actionlake.com/connectors/strangebee-thehive)
- [GitGuardian 12](https://actionlake.com/connectors/gitguardian)
- [Expel Workbench 10](https://actionlake.com/connectors/expel-workbench)

Joins with, on shared entities

- [HaloPSA 2](https://actionlake.com/connectors/halopsa)
- [Fortinet FortiGate 2](https://actionlake.com/connectors/fortinet-fortigate)
- [Genesys Cloud CX 2](https://actionlake.com/connectors/genesys-cloud-cx)
- [Commvault Cloud 2](https://actionlake.com/connectors/commvault-cloud)
- [Delinea Secret Server 2](https://actionlake.com/connectors/delinea-secret-server)
- [Docebo 2](https://actionlake.com/connectors/docebo)

Browse

- [All Identity & security connectors](https://actionlake.com/connectors/category/identity-and-security)
- [All connectors](https://actionlake.com/connectors)
- [How actionlake compares](https://actionlake.com/compare)

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

## Give your agent Torq today.

[Connect Torq 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/torq
More: https://actionlake.com/llms.txt