Outils AI Rank Lab, intégrés à votre agent IA
Le serveur MCP d'AI Rank Lab expose les mêmes outils que l'API développeur — le vérificateur complet SEO + AEO + GEO, la recherche Google en direct, les recherches AI Overview et AI Mode pour n'importe quel pays et appareil, la recherche de mots-clés, les Core Web Vitals, les vérifications de visibilité de marque par IA, la génération de FAQ et de llms.txt, ainsi que vos données Google Analytics 4, Search Console, de visites de bots et de citations — via le Model Context Protocol. Ajoutez-le à Claude Code, Claude Desktop ou Cursor, et votre agent pourra les exécuter directement.
Introduction
The Model Context Protocol (MCP) is an open standard that lets AI assistants call external tools. Our MCP server is a thin layer over the /api/v1 API REST: same tools, same credit billing, same account — but callable by Claude, Cursor, or any other MCP-compatible client as part of a conversation.
The server uses the HTTP Streamable transport in stateless mode, so there is nothing to install or host — you point your client at the endpoint with your API credentials.
Endpoint et authentification
Le serveur est accessible via un unique endpoint :
POST https://www.airanklab.com/api/v1/mcpEvery request must carry the same two headers as the REST API: x-api-key and x-api-secret. Generate both from Tableau de bord → API & Intégrations.
Votre configuration client MCP stocke le secret en texte clair sur votre machine. Gardez le fichier de configuration en dehors du contrôle de version, et faites pivoter la paire de clés depuis le tableau de bord si elle venait à fuiter.
Claude.ai (Application Web)
To connect the MCP server directly in the Claude.ai web interface, open the Ajouter un connecteur personnalisé dialog. Claude.ai does not support custom headers, so your credentials go in the URL query string instead.
Paste the following URL into the URL du serveur MCP distant field, replacing the placeholders with your actual API key and secret. Leave the Advanced OAuth fields blank.
https://www.airanklab.com/api/v1/mcp?x-api-key=YOUR_API_KEY&x-api-secret=YOUR_API_SECRETPuisque Claude.ai ne prend pas en charge les en-têtes personnalisés, vous devez inclure vos identifiants dans les paramètres de requête de l'URL. Sachez que cela pourrait les faire apparaître dans les journaux d'accès de notre serveur.
Use the URL exactly as shown — the www. host and no /sse suffix. Claude.ai connects over Streamable HTTP and posts to the exact URL you paste; a different host or path returns an error, and Claude then falls back to an OAuth sign-in flow that this server does not offer.
Claude Code
Une seule commande ajoute le serveur à Claude Code (CLI v1.x ou ultérieure) :
claude mcp add --transport http airanklab https://www.airanklab.com/api/v1/mcp \
--header "x-api-key: YOUR_API_KEY" \
--header "x-api-secret: YOUR_API_SECRET"Then ask Claude Code things like « exécuter l'audit SEO + AEO + GEO sur
example.com et résumer les problèmes critiques » or « qui est cité par la Vue d'ensemble IA de Google pour « meilleur CRM pour les startups » en Inde sur
mobile ? » — it will call the seo-aeo-geo-audit and google-ai-overview tools for you.
Claude Desktop
Add this to your Claude Desktop configuration (Paramètres → Développeur → Modifier la configuration, file claude_desktop_config.json), then restart the app:
{
"mcpServers": {
"airanklab": {
"url": "https://www.airanklab.com/api/v1/mcp",
"headers": {
"x-api-key": "YOUR_API_KEY",
"x-api-secret": "YOUR_API_SECRET"
}
}
}
}Cursor
Add the same block to ~/.cursor/mcp.json (global) or .cursor/mcp.json in your project:
{
"mcpServers": {
"airanklab": {
"url": "https://www.airanklab.com/api/v1/mcp",
"headers": {
"x-api-key": "YOUR_API_KEY",
"x-api-secret": "YOUR_API_SECRET"
}
}
}
}Outils disponibles et tarifs
Les outils MCP reproduisent les points d'accès des outils REST un à un et consomment le même solde de crédits — un outil coûte le même prix, que vous l'appeliez depuis le tableau de bord, l'API REST ou MCP. Les lectures de données sont gratuites ; les appels d'outils échoués sont remboursés automatiquement.
The three Google tools (google-search, google-ai-overview, google-ai-mode) take a Pays and a Appareil— name the country (“India”), its ISO code (“IN”) or its numeric location code (2356), and pick Ordinateur de bureau or Mobile. Results differ markedly between the two, so measure the one your buyers actually use. The search-locations tool lists every supported market. The GA4 and Search Console tools are free because they read your own Google data — connect those accounts in the dashboard first.
ai-citation-check asks ChatGPT, Perplexity, Claude and Gemini the same question in one call and reports which of them cite you — it is billed per engine, so naming fewer engines costs less. The backlink tools (backlinks-overview, backlinks-history, backlinks-list, domaines-referents, texte-d-ancrage, autorite-de-domaine-en-masse) work on toutdomain, not just the ones registered on your account, so an agent can research a competitor’s link profile directly. The free filtres-de-backlinks tool lists the presets, modes and fields the filtered backlink queries accept.
| Outil | Description | Crédits par appel |
|---|---|---|
ai-citation-check | Ask ChatGPT, Perplexity, Claude and Gemini one question and see who cites you | 100 per engine |
backlinks-list | Every individual backlink, with anchors, authority and spam signals | 150 |
seo-aeo-geo-audit | Full SEO + AEO + GEO checker — the same three-pillar report as the dashboard | 50 |
audits | Technical + AEO audit of a single URL | 50 |
google-search | Live Google SERP for one query, by country and device | 100 |
google-ai-overview | Google's AI Overview answer and the sources it cites | 100 |
google-ai-mode | Google's AI Mode conversational answer and its sources | 100 |
brand-visibility | Ask a live AI engine about a brand | 100 per engine |
keyword-research | Keyword volume, difficulty, intent and live SERP | 50 typical; billed per lookup |
core-web-vitals | Core Web Vitals / PageSpeed scan | 25 |
referring-domains | Domains linking to any site, ranked by authority | 25 |
anchor-text | Anchor text distribution and over-optimization signals | 25 |
bulk-domain-authority | Authority rank for up to 100 domains in one call | 25 |
faq-generator | Generate an FAQ plus FAQPage schema for a page | 20 |
llms-txt | Generate an llms.txt manifest | 20 |
backlinks-overview | Backlink profile summary for any domain: rank, referring domains, spam score | 15 |
backlinks-history | Month-by-month backlink trend with new and lost links | 15 |
backlink-filters | Filter presets, modes and fields the backlink tools accept | Free |
gsc-performance | Search Console clicks, impressions, CTR and position | Free |
gsc-sites | Your verified Search Console properties | Free |
ga4-report | Any GA4 metrics and dimensions over your property | Free |
ga4-realtime | GA4 activity in the last 30 minutes | Free |
ga4-properties | Your connected GA4 properties | Free |
tracking-stats | AI bot visit stats for your domain | Free |
citations | Where AI engines cite your site | Free |
search-locations | Countries, languages and devices the search tools accept | Free |
keyword-research-estimate | Preview a keyword-research cost before running it | Free |
credits | Current credit balance | Free |
Outils à exécution longue
Heavier tools (audits, brand visibility) normally finish within the request. Each call has a Budget de 120 secondes: if the work isn't done in time, the tool returns a jobId with polling instructions instead of the result.
Poll GET /api/v1/jobs/{jobId} (REST, same headers) until the status is terminé — see Tâches asynchrones in the API reference.
Limites de requêtes
MCP requests count against the same per-key limit as the REST API: 60 requêtes par minute by default. A 429 response includes Retry-After. Need a higher limit? Nous contacter.
Connectez votre agent
Générez votre clé et secret API, collez un bloc de configuration, et votre agent IA pourra exécuter de véritables outils de marketing.
Get your API key