Skip to content

IP73 MCP server

fr.ip73/ip73ip73.frstreamable-httpv1.0.0Scanned

French tech news, exploited vulnerabilities (KEV), cloud offers, AI models, scam guide. Read-only.

6 tools: 1 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 1 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

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 IP73 MCP server can do

The IP73 MCP server is published by ip73.fr, a domain the MCP Registry verified. It has 6 tools. It can create or change data (1 tool: latest_content), but cannot delete data. 5 tools only read.

1 tool brings in text other people can write (get_content); 1 tool can send data out of your system (get_content).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 13, 2026, version 1.0.0.

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.

6 tools

Changes things 1Claude Code: ask
  • latest_contentLes contenus les plus récents d’un type (article par défaut), du plus récent au plus ancien ; pour event, les prochains événements par date de début ; pour cloud_incident, par dern…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
    Les contenus les plus récents d’un type (article par défaut), du plus récent au plus ancien ; pour event, les prochains événements par date de début ; pour cloud_incident, par dernière mise à jour. Types : article (Articles d’actualité, 648), page (Pages, 16), cve (Vulnérabilités activement exploitées (KEV), 1781), scam (Fiches arnaques, 41), guide (Guides « Je suis victime », 9), model (Modèles d’IA, 283), crypto_platform (Plateformes crypto, 22), cloud_provider (Fournisseurs cloud, 25), cloud_offer (Offres cloud, VPS, serveurs dédiés, 566), cloud_incident (Incidents cloud, 1218), event (Événements tech, 202).

    Annotations the server declares

    • title: Derniers contenus IP73
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 5Show 5 read-only tools
  • compare_itemsCompare 2 à 5 éléments d’un même type comparable (model : Modèles d’IA ; crypto_platform : Plateformes crypto ; cloud_provider : Fournisseurs cloud ; cloud_offer : Offres cloud, VP…No findings

    Why it is in this group

    • The name "compare_items" says "compare": a word for reading.
    Description, as the server wrote it
    Compare 2 à 5 éléments d’un même type comparable (model : Modèles d’IA ; crypto_platform : Plateformes crypto ; cloud_provider : Fournisseurs cloud ; cloud_offer : Offres cloud, VPS, serveurs dédiés), attribut par attribut, uniquement avec les valeurs présentes dans les données d’IP73 : une valeur absente est null et listée dans missing, jamais estimée. Aucun score ni classement. Chaque élément cite ses sources et sa date de relevé. Trouver les identifiants avec search_content.

    Annotations the server declares

    • title: Comparer des éléments
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_contentLit un contenu public d’IP73 par son identifiant (champ id des résultats, ex.Reads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Lit un contenu public d’IP73 par son identifiant (champ id des résultats, ex. « article:2026/11/10/slug », « cve:CVE-2025-31324 », « scam:fausse-amende ») ou par son URL canonique https://ip73.fr/… (cherchée dans l’index, jamais téléchargée). Renvoie titre, URL canonique, dates, rubrique, sources et attribution ; le texte Markdown pour un article (découpé en parties : part), les détails structurés pour les autres types.

    Annotations the server declares

    • title: Lire un contenu IP73
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_contentRecherche lexicale déterministe dans tous les contenus publics d’IP73 : chaque mot de la requête doit apparaître (début de mot, sans tenir compte des accents ni de la casse) dans l…No findings

    Why it is in this group

    • The name "search_content" says "search": a word for reading.
    Description, as the server wrote it
    Recherche lexicale déterministe dans tous les contenus publics d’IP73 : chaque mot de la requête doit apparaître (début de mot, sans tenir compte des accents ni de la casse) dans le titre, le résumé, la rubrique, les mots-clés ou les champs ; tri par pertinence simple (mots trouvés dans le titre) puis par date. Pas de recherche sémantique. Types : article (Articles d’actualité, 648), page (Pages, 16), cve (Vulnérabilités activement exploitées (KEV), 1781), scam (Fiches arnaques, 41), guide (Guides « Je suis victime », 9), model (Modèles d’IA, 283), crypto_platform (Plateformes crypto, 22), cloud_provider (Fournisseurs cloud, 25), cloud_offer (Offres cloud, VPS, serveurs dédiés, 566), cloud_incident (Incidents cloud, 1218), event (Événements tech, 202). Résultats paginés (cursor), 20 au plus par page, 100 au plus au total. Lire un résultat avec get_content.

    Annotations the server declares

    • title: Rechercher dans IP73
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_cvesCherche dans le catalogue KEV de la CISA traduit par IP73 (vulnérabilités dont l’exploitation est confirmée par la CISA) : identifiant CVE, éditeur, produit, rançongiciel connu, CV…No findings

    Why it is in this group

    • The name "search_cves" says "search": a word for reading.
    Description, as the server wrote it
    Cherche dans le catalogue KEV de la CISA traduit par IP73 (vulnérabilités dont l’exploitation est confirmée par la CISA) : identifiant CVE, éditeur, produit, rançongiciel connu, CVSS minimal (NVD, quand publié), dates d’ajout. Sans critère : les dernières ajoutées. Le CVSS et l’EPSS sont null quand NVD ou FIRST ne les publient pas ; ils ne sont jamais estimés.

    Annotations the server declares

    • title: Vulnérabilités activement exploitées (KEV)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_scamsCherche dans le guide des arnaques d’IP73 : des fiches explicatives sur des TYPES d’arnaques en France (mode opératoire, signes, protection, que faire) et les guides « Je suis vict…No findings

    Why it is in this group

    • The name "search_scams" says "search": a word for reading.
    Description, as the server wrote it
    Cherche dans le guide des arnaques d’IP73 : des fiches explicatives sur des TYPES d’arnaques en France (mode opératoire, signes, protection, que faire) et les guides « Je suis victime ». Ce ne sont PAS des signalements : IP73 ne publie aucune liste de domaines, numéros ou personnes frauduleux, et ne qualifie jamais un site de frauduleux. Une organisation citée dans une fiche (ex. ANTAI, une banque) est en général celle dont l’identité est USURPÉE, pas l’auteur de l’arnaque. Pour vérifier un site ou signaler : les contacts officiels des guides (17Cyber, Pharos, Signal Conso…).

    Annotations the server declares

    • title: Fiches arnaques et guides victimes
    • 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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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 21, 2026, 19:21 UTC, unchanged since Nov 14, 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
2025-06-18
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://ip73.fr/mcp: tools/list returned 6 tools to an anonymous client, including latest_content (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ip73 https://ip73.fr/mcp
claude mcp add --transport http ip73 https://ip73.fr/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__ip73__search_content",
      "mcp__ip73__search_cves",
      "mcp__ip73__search_scams",
      "mcp__ip73__compare_items"
    ],
    "ask": [
      "mcp__ip73__get_content",
      "mcp__ip73__latest_content"
    ],
    "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 ip73. Review it before you use it.

Capability tags behind 1 rule
  • mcp__ip73__get_content untrusted-input, outbound

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/fr.ip73/ip73/verify?hash=a10a83e7814dc78602dc975a2f1a718d2370d374f1a64c161048691df3e5f8d2" | jq -e '.changed == false'

Pinned hash a10a83e7814d, from Nov 13, 2026, 22:18 UTC.

Watch

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

https://radar.anlyon.com/servers/fr.ip73/ip73/changes.xml

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

Badge

Anlyon Radar badge for fr.ip73/ip73
[![Anlyon Radar](https://radar.anlyon.com/badge/fr.ip73/ip73.svg)](https://radar.anlyon.com/servers/fr.ip73/ip73)

Source: MCP Registry. Synced Nov 13, 2026, 22:17 UTC.

IP73 MCP server: questions and answers

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

Is the IP73 MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the IP73 MCP server delete data?

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

Can the IP73 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 IP73 MCP server have?

6 tools: 1 write, 5 read. latest_content, search_content, get_content, search_cves, search_scams and compare_items.

Does the IP73 MCP server need sign-in or OAuth?

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

Does the IP73 MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_content.

Has the IP73 MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.