Integration · Developer tools

Connect Claude & ChatGPT to Action1

Ask your AI which computers are offline, which updates are missing or which endpoints are hit by a CVE, and get the answer from your Action1 organization. It can read endpoints, installed software, automations, run history and reports. It can also run an automation such as deploying updates or a reboot, and stop a running one, with your approval if you want it.

Connect Action1 free

Free plan, no credit card. Takes about a minute.

Try asking

“How many endpoints are offline or waiting for a reboot?”
The AI reads the endpoint status summary and lists the endpoints that are offline or need a reboot.
“Which critical updates are still missing across our machines?”
It lists missing updates filtered by security severity, with the package details for each one.
“Which computers are affected by CVE-2024-3400?”
It reads the vulnerability in your organization and lists the endpoints it was found on.

What your AI can do

Endpoints and software

List and filter managed endpoints and groups, see status, OS and last-seen details, and read installed software per endpoint or across the organization.

Updates and vulnerabilities

List missing updates by severity or approval status, read CVE details and see which endpoints each vulnerability affects.

Automations and reports

Read scheduled automations and run history, run or stop an automation, and pull the rows of any Action1 report.

“What software is installed on the laptop of our new designer?”
It finds the endpoint and lists the software installed on it.
“Did last night's patch automation succeed everywhere?”
It finds the automation run and lists the per-endpoint results, so you can see where it failed.
“Deploy the missing updates to the three finance PCs now.”
It looks up the action templates and runs an automation on those endpoints. This acts on the computers immediately.

27 tools for Action1

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

get_automationGet one scheduled automation by `automation_id`, with its actions, targets and schedule.
get_automation_runGet one automation run by its ID (`automation_id`).
get_current_userGet the settings of the user the connection is signed in as.
get_cve_descriptionGet the general description of a CVE by `cve_id`.
get_endpointGet one managed endpoint by `endpoint_id`, with OS, status, user and last-seen details.
get_endpoint_installed_softwareList the software installed on one endpoint (`endpoint_id`).
get_endpoint_status_summaryGet a summary of endpoint status (online, offline, needing updates or reboot) for the organization.
get_report_dataGet the rows of report `report_id`, optionally for one `endpoint_id`; filterable and paged.
get_update_packageGet missing-update details for one software package by `package_id`.
get_vulnerabilityGet details of one vulnerability in your organization by `cve_id`.
list_action_templatesList the available automation action templates (for example deploy updates, reboot, run script), with their IDs for run_automation.
list_automation_run_resultsList per-endpoint results for the automation run `instance_id`, filtered by `last_status`.
list_automation_runsList automation runs (history), filtered by `status`, `completed` or `endpoint_id`.
list_automationsList scheduled automations (policies) in the organization.
list_endpoint_groupsList endpoint groups in the organization.
list_endpoint_missing_updatesList updates missing on one endpoint (`endpoint_id`), filtered by `approval_status` or `security_severity`.
list_endpointsList managed endpoints (computers), filtered by `status`, `online_status`, `os`, `update_status`, `vulnerability_status` or `reboot_required`; paged with `from` and `limit`.
list_group_endpointsList the endpoints in the group `group_id`, with the same status filters as list_endpoints.
list_installed_softwareList installed software across all endpoints; filterable and paged.
list_missing_updatesList missing updates across the organization, filtered by `approval_status`, `security_severity` or SLA days.
list_organizationsList the Action1 organizations you can access, with their IDs.
list_reportsList available reports and report categories, with their IDs.
list_vulnerabilitiesList vulnerabilities (CVEs) found on endpoints, filtered by `score`, `remediation_status`, `endpoint_id` or published date.
list_vulnerable_endpointsList the endpoints affected by the vulnerability `cve_id`.
run_automationChanges dataRun an automation now: `name`, `actions` (template IDs and parameters), target `endpoints` and `retry_minutes`. Acts immediately on the target computers (for example installing updates or rebooting).
searchSearch the organization for endpoints, updates, software and more by free-text `query`.
stop_automation_runChanges dataStop a running automation by `instance_id`.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Action1 from the app list.
2
Paste your key
Paste your Action1 console host (app.action1.com for North America, or app.na-2.action1.com, app.eu.action1.com, app.uk.action1.com or app.au.action1.com), plus a Client ID and Client Secret. Create them on the API Credentials page in the Action1 console with the permissions you need; the secret is shown only once. Add your organization ID for calls that need one.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Action1?

It can read endpoints, endpoint groups, installed software, missing updates, vulnerabilities, automations, automation runs and reports, and search your organization. It can run an automation on chosen endpoints and stop a running one, if you switch those tools on.

Does the AI see my Action1 credentials?

No. Your Action1 Client ID and Client Secret are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start read-only. Running an automation acts on real computers right away, for example installing updates or rebooting, and it can require your approval before it runs. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Action1 account.

Which console host should I enter?

Enter the host of the region where your Action1 account lives: app.action1.com for North America, or app.na-2.action1.com, app.eu.action1.com, app.uk.action1.com or app.au.action1.com. It is the address you see in the browser when you are signed in to the Action1 console.