Connector guide6-minute read8 MCP tools7 languages

Connect ThreatAware to ChatGPT via MCP

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

HCBy HelpCode teamUpdated 6 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

ThreatAware

ThreatAware

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

tools

8

Region

INTL

Category

Monitoring

Authentication

API Key

Required env vars

THREATAWARE_CLOUD_IDTHREATAWARE_API_KEY
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Summary

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Guided setup

Connect ThreatAware to ChatGPT in 2 minutes

Start a free trial on AnythingMCP Cloud, connect ThreatAware in the guided setup, then add your MCP URL to ChatGPT. No code and no server to run.

No credit card · 7-day trial · Self-host alternative available

AnythingMCP's plugin in ChatGPT's directory answers questions from your company databases on AnythingMCP Cloud (PostgreSQL, MySQL, SQL Server, Oracle, SAP HANA, SQLite, MongoDB, read-only): open the listing (opens in a new tab) and click Install plugin. Every other connector is added to ChatGPT as a custom MCP server with your AnythingMCP MCP URL.

Try asking

Example prompts for ThreatAware

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

ThreatAware · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → ThreatAware, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

ThreatAware + ChatGPT

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

THREATAWARE_CLOUD_ID, THREATAWARE_API_KEY

Step 1 — Get credentials

Setting up takes about 3 minutes.

  1. Sign in to your portal and note the first part of its address: for https://acme-corp.threataware.com the Cloud ID is acme-corp. Put it into THREATAWARE_CLOUD_ID.
  2. Open Settings, API Access (address /settings/api) and click Generate Key. Name the key, pick an expiry (1 day, 1 week, 1 month or Never; the default is 1 day, so choose on purpose) and save.
  3. Copy the key at once (it is shown only once) into THREATAWARE_API_KEY. It is sent in the X-ThreatAware-ApiKey header.

The key sees what its creator sees. ThreatAware recommends creating it under a dedicated service user with a narrow role instead of a personal account.

Where to start

  • threataware_list_vitals shows every connected tool with its internal name (key) and, where Vitals is on, how many devices have the agent deployed, working and correctly configured. Read the three pairs as a funnel: deployed out of expected, functioning out of deployed, configured out of functioning.
  • threataware_list_alerts with filter allunresolved lists what is open now; state Red is urgent, Amber is a warning.
  • threataware_list_devices is the merged device inventory. SecurityTools on a device shows the alert counts per tool, ConnectedSystems where the device is known.
  • threataware_list_users is the merged list of people, with MFA and admin flags in metadata and the last successful and failed sign-in.
  • threataware_list_inventory returns one tool's raw records when you need a field the merged lists do not have. It needs the tool's internal name, which is the key from threataware_list_vitals and not always the name shown in the portal (Microsoft Intune is devices_msgraph, SCCM is mecmsystem).
  • Portal administration: threataware_list_portal_users, threataware_list_roles and threataware_list_teams describe who can sign in to ThreatAware and with which rights.

Paging: every list takes offset and limit and answers total. ThreatAware returns the whole data set when no limit is sent, so this connector always sends one (100 by default). On devices and users the offset stops at 10,000 records (status 400 beyond that); narrow with filter instead.

Reading the data

  • Times are ISO 8601 without a time zone, e.g. 2026-10-10T08:49:28.0000000. 0001-01-01T00:00:00 means "never" (not acknowledged, not resolved, not snoozed).
  • There are no server-side searches by host name, user or severity: fetch pages and filter the result yourself.
  • Device and user data is personal data (names, emails, IP addresses, sign-in locations). Share only what the question needs.

Limits and errors: 50 requests per minute for the whole portal, whichever key is used; status 429 means wait a minute. Status 400 with "Unexpected error occurred." means the key is wrong, disabled or expired (ThreatAware answers 400, not 401, for a bad key). 401 means no key was sent. 403 means the key's user lacks the permission for that area. A portal address that does not resolve means the Cloud ID is wrong.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

  1. Go to chatgpt.com/plugins, click Add, then Add custom MCP server.
  2. Enter a name, e.g. Name: ThreatAware.
  3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
  4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
  5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

ToolWhat it does
threataware_list_devicesList the devices ThreatAware has merged from all connected tools. Each device has id, hostName, os, osVersion, lastOnline, firstSeen…
threataware_list_usersList the people ThreatAware has collected from the connected directories and identity providers. Each user has id, name, email, jobTitle…
threataware_list_alertsList the alerts (issues) ThreatAware raised across the environment. Each alert has state (Red, Amber or Green), product (tool and…
threataware_list_inventoryRead the raw records ThreatAware holds for one connected tool, in that tool's own field names (for example Automox patch counts, or…
threataware_list_vitalsGet the health of every connected security tool (Vitals), today or on a past day. Each entry has key (the internal tool name used by the…
threataware_list_portal_usersList the accounts that can sign in to the ThreatAware portal itself (not the people found in the directories: for those call…
threataware_list_rolesList the roles of the ThreatAware portal. Each role has id (for example superAdmin, analyst or viewer), name, description, default (true…
threataware_list_teamsList the teams of the ThreatAware portal with their members. Each team has id, name and members (username, name and surname). Teams scope…

Example prompts

  • "Which security tools have the biggest gap between expected and deployed devices?"
  • "List all unresolved Red alerts."
  • "Which users have no MFA but admin rights?"
  • "Show the devices that are missing the EDR agent."
  • "Who can sign in to our ThreatAware portal, and with which roles?"

FAQ

Where do the Cloud ID and API key come from? The Cloud ID is the first part of your portal address (acme-corp for acme-corp.threataware.com). Create the key under Settings, API Access, Generate Key, pick its expiry on purpose (the default is 1 day) and copy it at once. The key sees what its creator sees, so ThreatAware recommends a dedicated service user with a narrow role.

What does it cover? The merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals: deployed, functioning, configured, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. There are no server-side searches by host name, user or severity; the AI pages through the lists and filters them.

Can it change anything? No. The ThreatAware API v1 accepts read requests only, so nothing can be changed, resolved or deleted, and nothing installs switched off. The whole portal shares 50 requests per minute.

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

Was this guide helpful?

Connect ThreatAware to ChatGPT in 2 minutes

Start a free trial on AnythingMCP Cloud, connect ThreatAware in the guided setup, then add your MCP URL to ChatGPT. No code and no server to run.

Related guides

Connectors

Connect ThreatAware to Claude via MCP

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Connectors

Connect ThreatAware to Microsoft Copilot via MCP

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Connectors

Connect ThreatAware to Cursor via MCP

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Connectors

Connect ThreatAware to Gemini CLI via MCP

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Connectors

Connect ThreatAware to Meta Muse via MCP

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.

Connectors

ThreatAware MCP Server: Devices, Alerts and Vitals

ThreatAware cyber asset management from any AI agent: the merged device and user inventory across your security and IT tools, open alerts, the health of each security control (Vitals, today or on a past day), the raw records of one connected tool, and the portal users, roles and teams. Read-only. Cloud ID and API key.