The CloudRadial AutomationAI Huntress extension lets a workflow or agent read your Huntress EDR and MDR data: the organizations you protect, the agents deployed in them, incident reports and detection signals, and summary and billing reports. With approval, it can also resolve an incident report once its remediations are approved in Huntress. This article covers what the extension can do, the API credentials it needs, which tool requires approval, and the skills that ship with it. It is for workspace users who build automations (Admin or Owner Role).
- What the Extension Covers
- Creating the API Credentials
- Providing the Credentials to Your Runner
- Reads and Approval-Gated Changes
- Skills
- Tips for Working With Huntress Data
What the Extension Covers
The extension calls the Huntress public REST API and provides 14 tools across these areas:
| Area | What you can automate |
| Account | Read the Huntress account the API credentials belong to, which also confirms the credentials work |
| Organizations and agents | List and read the organizations (customers) you protect, and list and read deployed agents, filtered by organization or platform (Windows or macOS) |
| Incident reports | List and read incident reports, filtered by organization, agent, status, severity, indicator type, or platform, and resolve an incident report |
| Signals | List and read the lower-level detection signals behind incidents, filtered by entity, signal type, or status |
| Reports | List and read monthly, quarterly, and yearly summary reports, and list and read billing reports filtered by status |
Install it from Extensions like any other catalog extension. It appears in the catalog as Huntress. See Browsing and installing extensions for the general install flow.
Creating the API Credentials
The extension signs in to Huntress with an API key pair: an API key and a secret key. In the Huntress portal, go to Account Settings > API Credentials and generate a key pair. Huntress shows the secret key only once, when the pair is created, so copy it immediately.
Providing the Credentials to Your Runner
Store three secrets in your runner's Key Vault with these exact names:
| Secret | Value |
Huntress-ApiUrl |
The Huntress API base URL, normally https://api.huntress.io/v1 |
Huntress-ApiKey |
The API key from the key pair you generated |
Huntress-ApiSecret |
The secret key from the same key pair |
The extension combines the API key and secret key into the sign-in Huntress expects on every request, so store each value exactly as Huntress issued it. For how to add secrets, see Accessing and updating your runner's Key Vault.
The agent reads the credentials from the runner and never asks you for them. Once the secrets are in place, ask the AI Playground which Huntress account the extension is connected to, to confirm the connection works.
Reads and Approval-Gated Changes
Of the 14 tools, 13 are read-only and run without interruption. The one tool that changes data, resolving an incident report, is approval-gated: the run pauses and the request appears as an Action Required item in the Inbox until someone approves it. See Handling Action Required items in the Inbox.
| Tool behavior | Tools |
| Approval-gated | Resolve an incident report |
| Read-only | Read the account; list and read organizations, agents, incident reports, signals, summary reports, and billing reports |
Huntress accepts a resolution only when every remediation on the incident report is already approved in the Huntress portal. The extension does not approve remediations, so approve them in Huntress first. If Huntress rejects the resolution, the agent reports the error rather than retrying.
Skills
The extension ships three skills that guide an agent through common Huntress tasks:
| Skill | Use it to |
| Review Security Incidents | Triage, list, or read incident reports and detection signals for an organization or agent. The agent resolves an incident report only when you ask it to and confirm its remediations are approved in Huntress. |
| Inventory Agents & Organizations | List or look up the organizations you protect and the agents deployed in them, or confirm which account the API key belongs to. Read-only. |
| Pull Reports | Pull monthly, quarterly, or yearly summary reports, or billing reports, for reconciliation, dashboards, or a customer review. Read-only. |
To give an agent these skills, see Creating custom agents and using them in workflows.
Tips for Working With Huntress Data
- Refer to customers and devices by name and let the agent look up the organization or agent id. It searches the list rather than guessing an id.
- List tools return the complete result in one call, so you do not pass a page number. Filter by organization to keep results focused.
- Incident reports can be filtered by status (sent, closed, or dismissed), severity (critical, high, or low), and platform (Windows, macOS, or Microsoft 365)
- Billing reports can be filtered by status: open, paid, failed, partial refund, or full refund
- If every call fails, check that all three secrets are set with the exact names above and that the API key and secret key come from the same key pair
If you are still having trouble, we’re here to help! Submit a ticket here for assistance, and don’t forget to check our status page to ensure there are no outages in your area.
Comments
0 comments
Please sign in to leave a comment.