--- title: "ThreatLocker MCP server for AI agents - actionlake" description: "Give Claude 94 ThreatLocker actions through one MCP server: computers, approval requests. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/threatlocker updated: 2026-10-23 --- Connectors · MSP & PSA # ThreatLocker MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to ThreatLocker and the rest of your systems. It gives your agent 94 ThreatLocker actions (60 reads, 25 writes and 9 that wait for a confirmation) and holds the ThreatLocker credential itself, so the agent never does. It paces ThreatLocker's limits and records every call. [Connect ThreatLocker 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: "threatlocker.action_logs.list_file_history", intent: "check which ThreatLocker account is connected" } # List file history entries from the action log · read · 1 upstream call ``` - 94 actions in one signed file - 60 read look, never change - 25 write create and update - 9 wait for a yes destructive, confirmed first Set up ## Connect ThreatLocker 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 ThreatLocker. 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. - `api_key` ThreatLocker API token: in the ThreatLocker portal create an API user (Administrators > API users) and copy its token - `host` Where your ThreatLocker lives: your host - `managed_organization_id` Your ThreatLocker managed organization id ``` account { op: "connections.requirements", service: "threatlocker" } # 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: "threatlocker.action_logs.list_file_history" } # list file history entries from the action log · read · 1 upstream call check { action: "threatlocker.computers.update", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` ThreatLocker 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** `api_key` **Setup fields** `host` `managed_organization_id` **Limits we pace to** 300 calls a minute, per connection **API covered** ThreatLocker Portal API v1 (public Swagger, OpenAPI 3.0.4)`portalapi.g.threatlocker.com` **Built from** ThreatLocker's documentation, read 23 October 2026[portalapi.g.threatlocker.com](https://portalapi.g.threatlocker.com/swagger/public/swagger.json) [threatlocker.kb.help](https://threatlocker.kb.help/) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 57 of 60 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 2, so ask can line ThreatLocker up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in ThreatLocker. 94 actions in 20 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **60** read look, never change - **25** write create and update - **9** destructive wait for a confirmation 1. ### Computers 19 7 read · 7 write · 5 destructive Search computers · Get a computer · Update a computer · List ThreatLocker agent versions in use 2. ### Approval requests 14 6 read · 8 write · 0 destructive Search approval requests · Authorize an approval request for permitting · Auto-permit the application in an approval request · Count pending approval requests 3. ### Action logs 9 9 read · 0 write · 0 destructive List file history entries from the action log · List file history entries from the action log (v2) · Search the unified audit (action log) · Get an action log entry 4. ### Scheduled agent actions 7 4 read · 2 write · 1 destructive Schedule an agent action · List scheduled agent actions · List targets a scheduled agent action can apply to · Search scheduled agent actions 5. ### Applications 6 6 read · 0 write · 0 destructive List applications available for maintenance mode · List application options for an organization · Find applications matching a file, hash, path or certificate · Get an application 6. ### Ringfence policies 6 5 read · 1 write · 0 destructive Check eligibility for advanced Ringfencing · Convert an application's legacy Ringfencing policy · Get a Ringfencing policy · Get the agent version required for advanced Ringfencing 7. ### Computer groups 4 4 read · 0 write · 0 destructive List computer groups and their computers · List computer groups for an organization (dropdown) · List computer groups for an installer download · List computer groups for permitting an application 8. ### Maintenance modes 4 1 read · 3 write · 0 destructive Create a maintenance mode · List maintenance modes for a computer · End a maintenance mode · Change a maintenance mode's end date **12 more areas · 25 actions** - Organizations **4** - Saved searches **3** - Saved TQL searches **3** - System audits **3** - Tags **3** - Reports **2** - Upload requests **2** - Computer checkins **1** - Online devices **1** - Policies **1** - Threatlocker versions **1** - Vdi hyperv **1** Top actions ## The ThreatLocker API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 7 of ThreatLocker's 7 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `threatlocker.computers.search` Search computers | Search computers. | read | `device.endpoint.search` 8 connectors | | `threatlocker.computers.get` Get a computer | Get a computer. | read | `device.endpoint.get` 57 connectors | | `threatlocker.organizations.search_children` Search child organizations | Search child organizations. | read | `crm.company.search` 36 connectors | | `threatlocker.computers.update` Update a computer | Update a computer. | write | `device.endpoint.update` 23 connectors | | `threatlocker.reports.list` List reports | List reports. | read | `analytics.report.list` 37 connectors | | `threatlocker.policies.get` Get a policy | Get a policy. | read | `security.policy.get` 30 connectors | | `threatlocker.system_audits.search` Search the system audit | Search the system audit. | read | `identity.audit_event.search` 7 connectors | | `threatlocker.action_logs.search` Search the unified audit (action log) | Search the unified audit (action log). | read | this connector | | `threatlocker.computers.list_versions` List ThreatLocker agent versions in use | List ThreatLocker agent versions in use. | read | this connector | | `threatlocker.approval_requests.ignore` Ignore approval requests | Ignore approval requests. | write | this connector | | `threatlocker.approval_requests.permit` Permit the application in an approval request | Permit the application in an approval request. | write | this connector | | `threatlocker.computers.restart_service` Restart the ThreatLocker service on computers | Restart the ThreatLocker service on computers. | destructive | this connector | Try it ## Prompts to paste into Claude. Each one names the ThreatLocker actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Which ThreatLocker devices have not checked in for a week? calls `threatlocker.computers.search` 2. Write write Update a computer in ThreatLocker. Show me exactly what you will send before you save it. calls `threatlocker.computers.update` 3. Across systems read Which ThreatLocker companies have invoices in NetSuite, and how many each? calls `threatlocker.organizations.search_children` `netsuite.views.invoices` Across your systems ## ThreatLocker, joined to the rest of your business. One `ask` fetches from ThreatLocker and another system, joins the rows on the same customer on our side, and hands your agent the answer, not every row. - Which ThreatLocker companies have invoices in NetSuite, and how many each? `threatlocker.organizations.search_children` + `netsuite.views.invoices`, on `crm.company` · [NetSuite](https://actionlake.com/connectors/netsuite) - Which ThreatLocker companies have tickets in HubSpot CRM, and how many each? `threatlocker.organizations.search_children` + `hubspot_crm.tickets.list`, on `crm.company` · [HubSpot CRM](https://actionlake.com/connectors/hubspot-crm) Also mapped by other connectors `crm.company` **227** `device.endpoint` **69** ask ``` ask { intent: "which ThreatLocker companies have invoices in NetSuite, and how many each", steps: [ { action: "threatlocker.organizations.search_children", 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 ThreatLocker ## Destructive actions wait for a yes. 9 ThreatLocker actions are destructive. These are all of them: - Restart the ThreatLocker service on computers `threatlocker.computers.restart_service` - Disable protection on computers (maintenance mode) `threatlocker.computers.disable_protection` - Move computers to another organization `threatlocker.computers.move_to_organization` - Regenerate the organization's install (auth) key `threatlocker.organizations.regenerate_auth_key` - Restart the ThreatLocker service on an organization's computers `threatlocker.computers.restart_service_for_organization` - Remove duplicate computers `threatlocker.computers.remove_duplicates` - Delete a saved search `threatlocker.saved_searches.delete` - Delete a saved TQL search `threatlocker.saved_tql_searches.delete` - Abort a scheduled agent action `threatlocker.scheduled_agent_actions.abort` 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 threatlocker.computers.remove_duplicates confirm_policy: **human** Remove duplicate computers? **intent:** the user asked me to remove duplicate computers run suspended · waiting for a named person · key _threatlocker-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "threatlocker-agent", allowed_actions: ["threatlocker.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "threatlocker.computers.restart_service", approver: "lead@example.com" }, { match: "threatlocker.computers.disable_protection", approver: "lead@example.com" }, { match: "threatlocker.computers.move_to_organization", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to ThreatLocker only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What ThreatLocker costs on actionlake. Every ThreatLocker action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call ThreatLocker 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 94 ThreatLocker actions - 94 actions page each page of a long list is one call - 57 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 ThreatLocker action. 94 actions by area: the id your agent calls, what it does, and its effect. **Computers 19** - `threatlocker.computers.disable_protection` Disable protection on computers (maintenance mode) destructive - `threatlocker.computers.enable_protection` Enable protection on computers write - `threatlocker.computers.finish_maintenance_mode` Finish maintenance mode on a computer write - `threatlocker.computers.get` Get a computer read - `threatlocker.computers.get_download` Get agent installer download details read - `threatlocker.computers.get_install_info` Get install details for a new computer read - `threatlocker.computers.get_os_types` Get operating system types for computers read - `threatlocker.computers.get_throttle_status` Get throttle status for computers read - `threatlocker.computers.list_versions` List ThreatLocker agent versions in use read - `threatlocker.computers.move_to_organization` Move computers to another organization destructive - `threatlocker.computers.remove_duplicates` Remove duplicate computers destructive - `threatlocker.computers.rescan_baseline` Rescan the baseline of computers write - `threatlocker.computers.restart_service` Restart the ThreatLocker service on computers destructive - `threatlocker.computers.restart_service_for_organization` Restart the ThreatLocker service on an organization's computers destructive - `threatlocker.computers.search` Search computers read - `threatlocker.computers.update` Update a computer write - `threatlocker.computers.update_channel` Update the update channel of computers write - `threatlocker.computers.update_maintenance_mode` Update a computer's maintenance mode write - `threatlocker.computers.update_version` Update the ThreatLocker agent version on computers write **Approval requests 14** - `threatlocker.approval_requests.authorize_for_permit` Authorize an approval request for permitting write - `threatlocker.approval_requests.auto_permit` Auto-permit the application in an approval request write - `threatlocker.approval_requests.count` Count pending approval requests read - `threatlocker.approval_requests.get` Get an approval request read - `threatlocker.approval_requests.get_file_download_details` Get file download details for an approval request read - `threatlocker.approval_requests.get_permit_application` Get the permit-application view of an approval request read - `threatlocker.approval_requests.get_storage_approval` Get the storage approval view of an approval request read - `threatlocker.approval_requests.ignore` Ignore approval requests write - `threatlocker.approval_requests.permit` Permit the application in an approval request write - `threatlocker.approval_requests.permit_storage` Permit a storage (device) approval request write - `threatlocker.approval_requests.permit_temporarily` Temporarily permit the application in an approval request write - `threatlocker.approval_requests.reject` Reject approval requests write - `threatlocker.approval_requests.search` Search approval requests read - `threatlocker.approval_requests.take_ownership` Take ownership of an approval request write **Action logs 9** - `threatlocker.action_logs.get` Get an action log entry read - `threatlocker.action_logs.get_file_download_details` Get file download details for an action log entry read - `threatlocker.action_logs.get_policy_conditions_for_permit` Get policy conditions to permit an application from an action log entry read - `threatlocker.action_logs.get_search_string` Build the search string for action log parameters read - `threatlocker.action_logs.get_testing_environment_details` Get testing environment details for an action log entry read - `threatlocker.action_logs.get_v2` Get an action log entry (v2) read - `threatlocker.action_logs.list_file_history` List file history entries from the action log read - `threatlocker.action_logs.list_file_history_v2` List file history entries from the action log (v2) read - `threatlocker.action_logs.search` Search the unified audit (action log) read **Scheduled agent actions 7** - `threatlocker.scheduled_agent_actions.abort` Abort a scheduled agent action destructive - `threatlocker.scheduled_agent_actions.create` Schedule an agent action write - `threatlocker.scheduled_agent_actions.get` Get a scheduled agent action read - `threatlocker.scheduled_agent_actions.list` List scheduled agent actions read - `threatlocker.scheduled_agent_actions.list_applies_to` List targets a scheduled agent action can apply to read - `threatlocker.scheduled_agent_actions.search` Search scheduled agent actions read - `threatlocker.scheduled_agent_actions.update` Update a scheduled agent action write **Applications 6** - `threatlocker.applications.get` Get an application read - `threatlocker.applications.get_for_network_policy_process` Get an application for a network policy process read - `threatlocker.applications.get_research_details` Get ThreatLocker research details for an application read - `threatlocker.applications.list_for_maintenance_mode` List applications available for maintenance mode read - `threatlocker.applications.list_options` List application options for an organization read - `threatlocker.applications.search_matching` Find applications matching a file, hash, path or certificate read **Ringfence policies 6** - `threatlocker.ringfence_policies.check_eligibility` Check eligibility for advanced Ringfencing read - `threatlocker.ringfence_policies.convert_legacy` Convert an application's legacy Ringfencing policy read - `threatlocker.ringfence_policies.get` Get a Ringfencing policy read - `threatlocker.ringfence_policies.get_agent_version` Get the agent version required for advanced Ringfencing read - `threatlocker.ringfence_policies.has_legacy` Check whether applications or policies use legacy Ringfencing read - `threatlocker.ringfence_policies.opt_in` Opt in to advanced Ringfencing policies write **Computer groups 4** - `threatlocker.computer_groups.list` List computer groups and their computers read - `threatlocker.computer_groups.list_dropdown` List computer groups for an organization (dropdown) read - `threatlocker.computer_groups.list_for_download` List computer groups for an installer download read - `threatlocker.computer_groups.list_for_permit` List computer groups for permitting an application read **Maintenance modes 4** - `threatlocker.maintenance_modes.create` Create a maintenance mode write - `threatlocker.maintenance_modes.end` End a maintenance mode write - `threatlocker.maintenance_modes.list` List maintenance modes for a computer read - `threatlocker.maintenance_modes.update_end_date` Change a maintenance mode's end date write **Organizations 4** - `threatlocker.organizations.get_auth_key` Get the organization's install (auth) key read - `threatlocker.organizations.list_for_move_computers` List organizations computers can be moved to read - `threatlocker.organizations.regenerate_auth_key` Regenerate the organization's install (auth) key destructive - `threatlocker.organizations.search_children` Search child organizations read **Saved searches 3** - `threatlocker.saved_searches.create` Save a search write - `threatlocker.saved_searches.delete` Delete a saved search destructive - `threatlocker.saved_searches.list` List saved searches for a page read **Saved TQL searches 3** - `threatlocker.saved_tql_searches.create` Save a TQL search write - `threatlocker.saved_tql_searches.delete` Delete a saved TQL search destructive - `threatlocker.saved_tql_searches.list` List saved TQL searches for a page read **System audits 3** - `threatlocker.system_audits.list_login_attempt_filters` List login attempt filters for the Health Center read - `threatlocker.system_audits.search` Search the system audit read - `threatlocker.system_audits.search_health_center` Search login attempts for the Health Center read **Tags 3** - `threatlocker.tags.get` Get a tag read - `threatlocker.tags.list` List tags for an organization read - `threatlocker.tags.update` Update a tag write **Reports 2** - `threatlocker.reports.get_data` Run a report and get its data read - `threatlocker.reports.list` List reports read **Upload requests 2** - `threatlocker.upload_requests.create` Request a file upload from a computer write - `threatlocker.upload_requests.get` Get a file upload request read **Computer checkins 1** - `threatlocker.computer_checkins.search` Search a computer's check-ins read **Online devices 1** - `threatlocker.online_devices.list` List online devices read **Policies 1** - `threatlocker.policies.get` Get a policy read **Threatlocker versions 1** - `threatlocker.threatlocker_versions.list` List ThreatLocker agent versions read **Vdi hyperv 1** - `threatlocker.vdi_hyperv.get_testing_environment_details` Get VDI / Hyper-V testing environment details read Questions ## The ThreatLocker MCP server, answered. **Is there a ThreatLocker MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 94 ThreatLocker actions across computers, approval requests, action logs and scheduled agent actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by ThreatLocker. **What do I need to connect ThreatLocker?** ThreatLocker API token: in the ThreatLocker portal create an API user (Administrators > API users) and copy its token. Plus your host and your managed organization id. The free call account { op: "connections.requirements", service: "threatlocker" } lists exactly what to paste. **Can an AI agent delete or change things in ThreatLocker?** Only if its key allows it, and only with an explicit confirmation. 9 ThreatLocker actions are destructive, including restart the ThreatLocker service on computers, disable protection on computers (maintenance mode) and move computers to another organization. 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 ThreatLocker API limit?** actionlake paces every call to the limits in the ThreatLocker service file: 300 calls a minute per connection. Repeated reads are answered from cache (57 ThreatLocker actions can be), which never reaches ThreatLocker. **What does a ThreatLocker action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (94 ThreatLocker actions page). Cache hits, searches, dry runs and calls ThreatLocker 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 ThreatLocker API does it cover?** The ThreatLocker Portal API v1 (public Swagger, OpenAPI 3.0.4) at portalapi.g.threatlocker.com by default, or the base URL set when you connect. It is built from ThreatLocker's documentation as read on 23 October 2026. 94 actions in 20 areas, each one in the signed service file (version 1.0.0). **Can I combine ThreatLocker with my other systems?** Yes. ask joins ThreatLocker to NetSuite or HubSpot CRM on the same customer and returns the answer rather than every row. ThreatLocker maps crm.company, which 227 other connectors also map. **Does actionlake keep my ThreatLocker 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 ThreatLocker 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 ThreatLocker Shares the most action names with - [Bitdefender GravityZone 4](https://actionlake.com/connectors/bitdefender-gravityzone) - [Automox 3](https://actionlake.com/connectors/automox) - [ThreatDown Nebula 2](https://actionlake.com/connectors/threatdown-nebula) - [ThreatDown OneView 2](https://actionlake.com/connectors/threatdown-oneview) - [Admin By Request 1](https://actionlake.com/connectors/admin-by-request) - [Ubiquiti UniFi Site Manager API 1](https://actionlake.com/connectors/ubiquiti-unifi-site-manager-api) Joins with, on shared entities - [LimaCharlie 2](https://actionlake.com/connectors/limacharlie) - [HubSpot CRM 1](https://actionlake.com/connectors/hubspot-crm) - [Microsoft 365 Users 1](https://actionlake.com/connectors/microsoft-365-users) - [QuickBooks Online 1](https://actionlake.com/connectors/quickbooks-online) - [Salesforce Sales Cloud 1](https://actionlake.com/connectors/salesforce-sales-cloud) - [Xero 1](https://actionlake.com/connectors/xero) 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 ThreatLocker; the name is the vendor's own. Counts are from the ThreatLocker service file, version 1.0.0. ## Give your agent ThreatLocker today. [Connect ThreatLocker 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/threatlocker More: https://actionlake.com/llms.txt