Skip to content

AI Act Radar MCP server

com.aiactradar/ai-act-radaraiactradar.comstreamable-httpv0.2.2Scanned

EU AI Act obligations and updates from 22 official EU and national sources. No key needed.

4 tools: 1 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 1 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AI Act Radar MCP server can do

The AI Act Radar MCP server is published by aiactradar.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (1 tool: summarize_changes_since), but cannot delete data. 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

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

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 18, 2026, version 0.2.2.

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.

4 tools

Changes things 1Claude Code: ask
  • summarize_changes_sinceGenerate a structured digest of AI Act regulatory changes since a given date, grouped by severity, in English or German.1 finding

    Why it is in this group

    • The name "summarize_changes_since" says "summarize": a word for reading.
    • The description's first verb is "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "summarize_changes_since" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "summarize_changes_since" says "summarize": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Generate a structured digest of AI Act regulatory changes since a given date, grouped by severity, in English or German. Useful for weekly compliance reviews or audit prep. Returns Markdown plus event_count (events in the digest) and total_matching. Without a key the digest holds the 10 most severe events.

    Annotations the server declares

    • title: Summarize changes since a date
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • get_obligation_for_roleLook up the AI Act obligations for a specific role and AI-system risk category.No findings

    Why it is in this group

    • The name "get_obligation_for_role" says "get": a word for reading.
    Description, as the server wrote it
    Look up the AI Act obligations for a specific role and AI-system risk category. Returns the relevant articles, deadlines, official sources and the most recent events for the primary article. This is informational, not legal advice.

    Annotations the server declares

    • title: Obligations for a role and risk class
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • lookup_articleLook up a reference to Regulation (EU) 2024/1689 (e.g.No findings

    Why it is in this group

    • The name "lookup_article" says "lookup": a word for reading.
    Description, as the server wrote it
    Look up a reference to Regulation (EU) 2024/1689 (e.g. "Art. 53(1)(d)", "Annex III", "Recital 60") and return related events plus the EUR-Lex URL. Matches whole references: "Art. 5" finds Art. 5 and Art. 5(1)(b), never Art. 50. References the Regulation does not have (Art. 1 to 113, Annex I to XIII, Recital 1 to 180) return known: false and no EUR-Lex link.

    Annotations the server declares

    • title: Look up an AI Act article
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • query_ai_act_updatesQuery EU AI Act regulatory updates from primary sources, newest first.No findings

    Why it is in this group

    • The name "query_ai_act_updates" says "query": a word for reading.
    Description, as the server wrote it
    Query EU AI Act regulatory updates from primary sources, newest first. Filters (date range, source, topics, severity) apply to the whole register before limit. Every event has the same shape in all tools: id, source_id, event_type, severity, topics, title_en, title_de, summary_en, summary_de, url_official, url_kind ("official", or "secondary" where no official publication was found), ai_act_articles (array), version, published_at (ISO 8601).

    Annotations the server declares

    • title: Query AI Act updates
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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 private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:33 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2024-11-05
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.aiactradar.com/mcp/v1: tools/list returned 4 tools to an anonymous client, including summarize_changes_since (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "summarize_changes_since" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "summarize_changes_since" says "summarize": a word for reading.

    What this check looks for

History

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

  1. Tools4 changed.~4 changedView diff
  2. Tools4 changed.~4 changedView diff

Install

Pinned to version 0.2.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http ai-act-radar https://mcp.aiactradar.com/mcp/v1
claude mcp add --transport http ai-act-radar https://mcp.aiactradar.com/mcp/v1

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__ai-act-radar__query_ai_act_updates",
      "mcp__ai-act-radar__get_obligation_for_role",
      "mcp__ai-act-radar__lookup_article"
    ],
    "ask": [
      "mcp__ai-act-radar__summarize_changes_since"
    ],
    "deny": []
  }
}

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 ai-act-radar. Review it before you use it.

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/com.aiactradar/ai-act-radar/verify?hash=687a5573e44f36fd8a139c98c210e2679fb4e826e825a07d484477963b7d17dd" | jq -e '.changed == false'

Pinned hash 687a5573e44f, from Nov 18, 2026, 10:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.aiactradar/ai-act-radar/changes.xml

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

Badge

Anlyon Radar badge for com.aiactradar/ai-act-radar
[![Anlyon Radar](https://radar.anlyon.com/badge/com.aiactradar/ai-act-radar.svg)](https://radar.anlyon.com/servers/com.aiactradar/ai-act-radar)

Source: MCP Registry · repository. Synced Nov 18, 2026, 10:17 UTC.

AI Act Radar MCP server: questions and answers

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

Is the AI Act Radar MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 1 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 AI Act Radar MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AI Act Radar MCP server 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 AI Act Radar MCP server have?

4 tools: 1 write, 3 read. summarize_changes_since, query_ai_act_updates, get_obligation_for_role and lookup_article.

Does the AI Act Radar MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AI Act Radar MCP server send data to outside services?

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

Has the AI Act Radar MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.