Investigate security events and manage the allow/deny lists an analyst acts on. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"castle": {
"url": "https://castle.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"castle": {
"type": "http",
"url": "https://castle.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Castle API secret.
Find it in Castle → Settings → API. Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
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 Castle API 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.
Turn on the Castle connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
castle_get_events_schema | read | Get the event schema List the event fields you can filter and group on, with their types. Read this first — the other query tools need real field names. Castle: GET /v1/events/schema. |
castle_search_events | read | Search security events Query the security event stream — logins, registrations, transactions and their risk verdicts. Read-only despite being a POST: Castle takes the query in the body. Castle: POST /v1/events/query. |
castle_group_events | read | Group security events Aggregate matching events by one or more fields — the fast way to see which IPs, devices or countries dominate a spike. Read-only despite being a POST. Castle: POST /v1/events/group. |
castle_search_lists | read | Search lists Find the allow/deny lists defined in the environment. Read-only despite being a POST. Castle: POST /v1/lists/query. |
castle_get_list | read | Get one list Fetch a single list with its primary and secondary field definitions. Castle: GET /v1/lists/{id}. |
castle_search_list_items | read | Search items in a list Search the entries of one list — the blocked IPs, emails or device ids it holds. Read-only despite being a POST. Castle: POST /v1/lists/{list_id}/items/query. |
castle_count_list_items | read | Count items in a list Count the entries in one list, with the same optional filters as the search. Read-only despite being a POST. Castle: POST /v1/lists/{list_id}/items/count. |
castle_get_list_item | read | Get one list item Fetch a single list entry — its value, who added it, the comment and its archive time. Castle: GET /v1/lists/{list_id}/items/{id}. |
castle_create_list | write | Create a list Create a new allow or deny list. primary_field is the event field its entries match on, e.g. ip or user.email. Castle: POST /v1/lists. |
castle_update_list | write | Update a list Rename a list or change its colour or description. Castle: PUT /v1/lists/{id}. |
castle_create_list_item | write | Add an item to a list Add an entry to a list — for example block an IP or an email. This changes live policy behaviour. Castle: POST /v1/lists/{list_id}/items. |
castle_update_list_item | write | Update a list item's comment Change the comment on a list entry. Castle: PUT /v1/lists/{list_id}/items/{id}. |
castle_archive_list_item | write | Archive a list item Archive a list entry so it stops matching. Reversible with castle_unarchive_list_item. Castle: DELETE /v1/lists/{list_id}/items/{id}/archive. |
castle_unarchive_list_item | write | Unarchive a list item Restore a previously archived list entry so it matches again. Castle: PUT /v1/lists/{list_id}/items/{id}/unarchive. |
castle_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
castle_request_feature | Request a missing feature Tell usefulapi that the user needs something the Castle tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
castle_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Castle tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
castle_cancel_subscription | Cancel the Pro subscription Cancel the caller's Castle Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run castle_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
Pro covers this Castle server only. Subscribe with castle_upgrade (it returns a Stripe Checkout link). Cancel any time with castle_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running castle_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Castle. The server calls the Castle API with your own Castle access, so it sees only the data that your account can see.
The login page asks for your Castle API secret. See Before you connect for where to find it.
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 Castle API 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 Castle 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 Castle.
Yes, if you approve it. 6 of the 14 Castle tools can create or change data. The other 8 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Castle server only. Run castle_usage_status to see how many calls you used.
Ask the AI to run castle_upgrade: it returns a Stripe Checkout link. To cancel, run castle_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 castle_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, 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.