Skip to content

Castle MCP by usefulapi

io.usefulapi/castleusefulapi.iostreamable-httpv1.40.4Scanned

Investigate security events and manage the allow/deny lists an analyst acts on.

14 tools: 6 can delete or cancel things, 1 change things and 7 only read.

Tools: 6 delete, 0 irreversible, 1 write, 7 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 0
  • 1 finding

The remote endpoint did not answer the last look. Remote posture

Anlyon alternative

7 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Castle MCP by usefulapi can do

The Castle MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (6 tools: castle_create_list, castle_update_list, castle_create_list_item, castle_update_list_item and 2 more) and create or change data (1 tool: castle_group_events). 7 tools only read.

1 tool reads private data (castle_search_list_items); 2 tools bring in text other people can write (castle_search_list_items and castle_get_list_item).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Last scanned Oct 25, 2026, version 1.40.4.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

14 tools

Deletes or cancels 6Claude Code: deny
  • castle_archive_list_itemArchive a list entry so it stops matching.No findings

    Why it is in this group

    • The name "castle_archive_list_item" says "archive": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Archive a list entry so it stops matching. Reversible with castle_unarchive_list_item. Castle: DELETE /v1/lists/{list_id}/items/{id}/archive.

    Annotations the server declares

    • title: Archive a list item
    • destructiveHint: true
  • castle_create_listCreate a new allow or deny list.No findings

    Why it is in this group

    • The name "castle_create_list" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create a list
    • destructiveHint: true
  • castle_create_list_itemAdd an entry to a list — for example block an IP or an email.No findings

    Why it is in this group

    • The name "castle_create_list_item" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Add an item to a list
    • destructiveHint: true
  • castle_unarchive_list_itemRestore a previously archived list entry so it matches again.1 finding

    Why it is in this group

    • The name "castle_unarchive_list_item" says "list": a word for reading.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Warn

      The server marks "castle_unarchive_list_item" destructive (destructiveHint: true), and its name says "list", a word for reading.

      Matched text

      annotations: {"destructiveHint":true}; The name "castle_unarchive_list_item" says "list": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Restore a previously archived list entry so it matches again. Castle: PUT /v1/lists/{list_id}/items/{id}/unarchive.

    Annotations the server declares

    • title: Unarchive a list item
    • destructiveHint: true
  • castle_update_listRename a list or change its colour or description.No findings

    Why it is in this group

    • The name "castle_update_list" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Rename a list or change its colour or description. Castle: PUT /v1/lists/{id}.

    Annotations the server declares

    • title: Update a list
    • destructiveHint: true
  • castle_update_list_itemChange the comment on a list entry.No findings

    Why it is in this group

    • The name "castle_update_list_item" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Change the comment on a list entry. Castle: PUT /v1/lists/{list_id}/items/{id}.

    Annotations the server declares

    • title: Update a list item's comment
    • destructiveHint: true
Changes things 1Claude Code: ask
  • castle_group_eventsAggregate matching events by one or more fields — the fast way to see which IPs, devices or countries dominate a spike.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Group security events
    • readOnlyHint: true
Only reads 7Show 7 read-only tools
  • castle_count_list_itemsCount the entries in one list, with the same optional filters as the search.No findings

    Why it is in this group

    • The name "castle_count_list_items" says "count": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Count items in a list
    • readOnlyHint: true
  • castle_get_events_schemaList the event fields you can filter and group on, with their types.No findings

    Why it is in this group

    • The name "castle_get_events_schema" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get the event schema
    • readOnlyHint: true
  • castle_get_listFetch a single list with its primary and secondary field definitions.No findings

    Why it is in this group

    • The name "castle_get_list" says "get": a word for reading.
    Description, as the server wrote it
    Fetch a single list with its primary and secondary field definitions. Castle: GET /v1/lists/{id}.

    Annotations the server declares

    • title: Get one list
    • readOnlyHint: true
  • castle_get_list_itemFetch a single list entry — its value, who added it, the comment and its archive time.Reads text others writeNo findings

    Why it is in this group

    • The name "castle_get_list_item" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "fetch" and "comment": it reads comments, which other people can write.
    Description, as the server wrote it
    Fetch a single list entry — its value, who added it, the comment and its archive time. Castle: GET /v1/lists/{list_id}/items/{id}.

    Annotations the server declares

    • title: Get one list item
    • readOnlyHint: true
  • castle_search_eventsQuery the security event stream — logins, registrations, transactions and their risk verdicts.No findings

    Why it is in this group

    • The name "castle_search_events" says "search": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Search security events
    • readOnlyHint: true
  • castle_search_list_itemsSearch the entries of one list — the blocked IPs, emails or device ids it holds.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "castle_search_list_items" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "search" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "search" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Search items in a list
    • readOnlyHint: true
  • castle_search_listsFind the allow/deny lists defined in the environment.No findings

    Why it is in this group

    • The name "castle_search_lists" says "search": a word for reading.
    Description, as the server wrote it
    Find the allow/deny lists defined in the environment. Read-only despite being a POST. Castle: POST /v1/lists/query.

    Annotations the server declares

    • title: Search lists
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

The remote endpoint did not answer the last look

Looked at Nov 20, 2026, 19:33 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
no
HTTP status of an anonymous initialize
not observed
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: The server redirected a POST to a different request.

Posture changes

  1. Oct 29, 2026
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 7 to 0
    • Protocol version: 2025-06-18 to none
    • RFC 9728 protected resource metadata: https://castle.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
    • Authorization servers: https://castle.usefulapi.io to none
    • Dynamic client registration: yes to not observed
    • Client ID metadata documents: no to not observed

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "castle_unarchive_list_item" destructive (destructiveHint: true), and its name says "list", a word for reading.

    Matched text

    annotations: {"destructiveHint":true}; The name "castle_unarchive_list_item" says "list": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 6 more).View diff
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 7 to 0
    • Protocol version: 2025-06-18 to none
    • RFC 9728 protected resource metadata: https://castle.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
    • Authorization servers: https://castle.usefulapi.io to none
    • Dynamic client registration: yes to not observed
    • Client ID metadata documents: no to not observed

Install

Pinned to version 1.40.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http castle https://castle.usefulapi.io/mcp
claude mcp add --transport http castle https://castle.usefulapi.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__castle__castle_get_events_schema",
      "mcp__castle__castle_search_events",
      "mcp__castle__castle_search_lists",
      "mcp__castle__castle_get_list",
      "mcp__castle__castle_search_list_items",
      "mcp__castle__castle_count_list_items",
      "mcp__castle__castle_get_list_item"
    ],
    "ask": [
      "mcp__castle__castle_group_events"
    ],
    "deny": [
      "mcp__castle__castle_create_list",
      "mcp__castle__castle_update_list",
      "mcp__castle__castle_create_list_item",
      "mcp__castle__castle_update_list_item",
      "mcp__castle__castle_archive_list_item",
      "mcp__castle__castle_unarchive_list_item"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as castle. Review it before you use it.

Capability tags behind 2 rules
  • mcp__castle__castle_search_list_items private-data, untrusted-input
  • mcp__castle__castle_get_list_item untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.usefulapi/castle/verify?hash=fee04578f8da296eae76fd0ad3737c9ee087a1f3dfdd826d477be4c99f5d43cc" | jq -e '.changed == false'

Pinned hash fee04578f8da, from Oct 25, 2026, 23:19 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.usefulapi/castle/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.usefulapi/castle
[![Anlyon Radar](https://radar.anlyon.com/badge/io.usefulapi/castle.svg)](https://radar.anlyon.com/servers/io.usefulapi/castle)

Source: MCP Registry · repository. Synced Nov 18, 2026, 11:18 UTC.

Castle MCP by usefulapi: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Castle MCP by usefulapi safe?

No scan can promise that. What its definitions show: 14 tools, 7 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Castle MCP by usefulapi delete data?

Yes. 6 tools can delete, cancel or revoke something: castle_create_list, castle_update_list, castle_create_list_item, castle_update_list_item, castle_archive_list_item and castle_unarchive_list_item.

Can the Castle MCP by usefulapi do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Castle MCP by usefulapi have?

14 tools: 6 destructive, 1 write, 7 read. castle_create_list, castle_update_list, castle_create_list_item, castle_update_list_item, castle_archive_list_item, castle_unarchive_list_item, castle_group_events, castle_get_events_schema and 6 more.

Does the Castle MCP by usefulapi need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Castle MCP by usefulapi send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Castle MCP by usefulapi changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.