_ registry / mcp streamable-http · checked 1h ago

ip73

https://ip73.fr

Registry code: 5ffe09c9f3e349c6

api record

Serveur MCP public et en lecture seule d’IP73 (actualité tech en français). Contenus : article (Articles d’actualité), page (Pages), cve (Vulnérabilités activement exploitées (KEV)), scam (Fiches arnaques), guide (Guides « Je suis victime »), model (Modèles d’IA), crypto_platform (Plateformes crypto), cloud_provider (Fournisseurs cloud), cloud_offer (Offres cloud, VPS, serveurs dédiés), cloud_incident (Incidents cloud), event (Événements tech). Commencez par search_content ou latest_content, puis lisez un résultat avec get_content. Citez « IP73 » et l’URL canonique (champ url) de chaque…

endpoint
https://ip73.fr/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is ip73 live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is ip73 free to use?
Yes — the hub reached it with no key and no payment.
What tools does ip73 have?
6 tools: search_content, search_scams, compare_items, get_content, latest_content, search_cves.
Is ip73 safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
174ms

last good check

priced tools
0

of 6 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 6 tools
2 open 4 never probed 2 of 6 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • latest_content open 1h ago

    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, 659), 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, 1256), event (Événements tech, 195).

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "type": {
      "enum": [
        "article",
        "page",
        "cve",
        "scam",
        "guide",
        "model",
        "crypto_platform",
        "cloud_provider",
        "cloud_offer",
        "cloud_incident",
        "event"
      ],
      "type": "string",
      "default": "article"
    },
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 20,
      "minimum": 1
    },
    "cursor": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 200,
      "minLength": 1
    },
    "section": {
      "enum": [
        "agents",
        "arnaques",
        "assistants-outils",
        "protocoles",
        "business",
        "crypto-actifs",
        "developpement",
        "devops-cloud",
        "entreprises-business",
        "espace-science",
        "intelligence-artificielle",
        "jeux-video",
        "marches",
        "mlops-infrastructure",
        "modeles",
        "numerique-regulation",
        "securite-crypto-actifs",
        "plateformes",
        "regulation",
        "regulation-securite",
        "securite",
        "technologie",
        "telecoms-internet"
      ],
      "type": "string",
      "description": "Rubrique des articles (slug, sous-rubriques comprises)."
    }
  },
  "additionalProperties": false
}
    arguments 65 lines
  • search_cves open 1h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "to": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Ajoutée au catalogue jusqu’au (AAAA-MM-JJ)."
    },
    "cve": {
      "type": "string",
      "pattern": "^CVE-\\d{4}-\\d{4,}$",
      "maxLength": 30,
      "minLength": 9
    },
    "from": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Ajoutée au catalogue à partir de (AAAA-MM-JJ)."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1
    },
    "cursor": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 200,
      "minLength": 1
    },
    "vendor": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1
    },
    "product": {
      "type": "string",
      "maxLength": 100,
      "minLength": 1
    },
    "min_cvss": {
      "type": "number",
      "maximum": 10,
      "minimum": 0
    },
    "ransomware": {
      "enum": [
        "Known",
        "Unknown"
      ],
      "type": "string",
      "description": "Known : utilisation connue dans des campagnes de rançongiciel (selon la CISA)."
    }
  },
  "additionalProperties": false
}
    arguments 63 lines
  • search_content unknown never probed

    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, 659), 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, 1256), event (Événements tech, 195). Résultats paginés (cursor), 20 au plus par page, 100 au plus au total. Lire un résultat avec get_content.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "to": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Date de publication maximale (AAAA-MM-JJ)."
    },
    "from": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Date de publication minimale (AAAA-MM-JJ)."
    },
    "type": {
      "type": "array",
      "items": {
        "enum": [
          "article",
          "page",
          "cve",
          "scam",
          "guide",
          "model",
          "crypto_platform",
          "cloud_provider",
          "cloud_offer",
          "cloud_incident",
          "event"
        ],
        "type": "string"
      },
      "maxItems": 11,
      "minItems": 1,
      "description": "Limiter à ces types (tous par défaut)."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1
    },
    "cursor": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 200,
      "minLength": 1
    },
    "section": {
      "enum": [
        "agents",
        "arnaques",
        "assistants-outils",
        "protocoles",
        "business",
        "crypto-actifs",
        "developpement",
        "devops-cloud",
        "entreprises-business",
        "espace-science",
        "intelligence-artificielle",
        "jeux-video",
        "marches",
        "mlops-infrastructure",
        "modeles",
        "numerique-regulation",
        "securite-crypto-actifs",
        "plateformes",
        "regulation",
        "regulation-securite",
        "securite",
        "technologie",
        "telecoms-internet"
      ],
      "type": "string",
      "description": "Rubrique des articles (slug, sous-rubriques comprises) ; limite la recherche aux articles."
    }
  },
  "additionalProperties": false
}
    arguments 87 lines
  • search_scams unknown never probed

    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…).

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1
    },
    "cursor": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]+$",
      "maxLength": 200,
      "minLength": 1
    },
    "family": {
      "enum": [
        "banque",
        "administration",
        "livraison",
        "achat-vente",
        "investissement",
        "proches",
        "chantage",
        "piratage",
        "emploi",
        "entreprise"
      ],
      "type": "string",
      "description": "banque = Banque et paiement ; administration = Fausse administration ; livraison = Colis et livraison ; achat-vente = Achat et vente en ligne ; investissement = Placements et crypto ; proches = Proches et sentiments ; chantage = Chantage ; piratage = Piratage et virus ; emploi = Emploi ; entreprise = Entreprises"
    },
    "target": {
      "enum": [
        "tous",
        "seniors",
        "jeunes",
        "vendeurs",
        "acheteurs",
        "investisseurs",
        "voyageurs",
        "demandeurs-emploi",
        "entreprises"
      ],
      "type": "string",
      "description": "tous = Tout le monde ; seniors = Seniors ; jeunes = Jeunes ; vendeurs = Vendeurs en ligne ; acheteurs = Acheteurs en ligne ; investisseurs = Épargnants ; voyageurs = Vacanciers ; demandeurs-emploi = Chercheurs d’emploi ; entreprises = Entreprises"
    },
    "channel": {
      "enum": [
        "sms",
        "email",
        "telephone",
        "messagerie",
        "reseaux-sociaux",
        "site-web",
        "publicite",
        "courrier",
        "en-personne",
        "qr-code"
      ],
      "type": "string",
      "description": "sms = SMS ; email = E-mail ; telephone = Téléphone ; messagerie = WhatsApp, Telegram… ; reseaux-sociaux = Réseaux sociaux ; site-web = Site web ; publicite = Publicité en ligne ; courrier = Courrier ; en-personne = En personne ; qr-code = QR code"
    },
    "include_guides": {
      "type": "boolean",
      "default": true,
      "description": "Inclure les guides « Je suis victime » (que faire, qui contacter)."
    }
  },
  "additionalProperties": false
}
    arguments 76 lines
  • compare_items unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^[a-z_]{2,30}:[A-Za-z0-9._\\/:+@-]{1,250}$",
        "maxLength": 300,
        "minLength": 3
      },
      "maxItems": 5,
      "minItems": 2
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • get_content unknown 1h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z_]{2,30}:[A-Za-z0-9._\\/:+@-]{1,250}$",
      "maxLength": 300,
      "minLength": 3
    },
    "url": {
      "type": "string",
      "pattern": "^https:\\/\\/(www\\.)?ip73\\.fr\\/[^\\s]*$",
      "maxLength": 500,
      "minLength": 16
    },
    "part": {
      "type": "integer",
      "default": 1,
      "maximum": 200,
      "minimum": 1
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 5ffe09c9f3e349c6.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/5ffe09c9f3e349c6/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/5ffe09c9f3e349c6/badge.svg)](https://brick.blue/agent/5ffe09c9f3e349c6?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.