Read endpoints, missing updates, CVE vulnerabilities, installed software and reports in Action1. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.
Turn on the Action1 connector, then ask in plain words. The AI picks the tools.
For IT teams and service providers who patch and monitor endpoints in Action1.
List the organizations, then list the endpoints with status and reboot need. Open one endpoint for its OS and last-seen time.
List the updates that endpoints still miss, filtered by approval status and severity, across all organizations. Then list one package's updates to see the endpoints they affect.
List the CVEs found on endpoints, with CVSS score and deadline. Read one CVE for its CISA KEV flag, then list the endpoints it affects.
List the software installed across the endpoints of one organization. List automation runs with their status and completion.
List the report definitions your credentials can use. Read the rows of one report for one organization.
The login page asks for your Action1 region, Client ID and Client secret.
In Action1 open Configuration | Users & API Credentials and click New API Credentials. Give them a role that only reads what you need. Your credentials are used only to call the API on your behalf and to derive a private account id; they are never shown to anyone.
Team and Enterprise: an Owner adds the connector for the organization first.
No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"action1": {
"url": "https://action1.usefulapi.io/mcp"
}
}
} Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"action1": {
"type": "http",
"url": "https://action1.usefulapi.io/mcp"
}
}
} Run these commands. The second one opens the login page:
Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Action1 region, Client ID and Client secret. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Action1 server only. Subscribe with action1_upgrade (it returns a Stripe Checkout link). Cancel any time with action1_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running action1_upgrade before then undoes the cancel. Or write to [email protected].
action1_list_organizationsaction1_get_current_useraction1_searchaction1_list_endpointsaction1_get_endpointaction1_list_endpoint_groupsaction1_list_group_endpointsaction1_list_missing_updatesaction1_list_package_updatesaction1_list_vulnerabilitiesaction1_get_vulnerabilityaction1_list_vulnerability_endpointsaction1_list_installed_softwareaction1_list_automation_instancesaction1_list_reportsaction1_get_report_rowsaction1_usage_statusaction1_request_featureaction1_upgradeaction1_cancel_subscriptionFind endpoints that are offline or need a reboot. List missing critical updates. Check whether a CVE affects your endpoints. Review installed software and automation runs. Read Action1 reports. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Action1. The server calls the Action1 API with your own Action1 access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Action1 region, Client ID and Client secret. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Action1 region, Client ID and Client secret. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Action1 API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Action1.
All 16 Action1 tools are marked read-only.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Action1 server only. Cancel any time: Pro then runs to the end of the paid period. Run action1_usage_status to see how many calls you used.
Ask the AI to run action1_upgrade: it returns a Stripe Checkout link. To cancel, run action1_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with action1_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.