Miss deine KI-Sichtbarkeit, bevor du sie optimierst.
mcp-geo erzeugt echte Fragen, fragt mehrere Suchsysteme ab und speichert Zitate deiner Marke und deiner Wettbewerber. So wird SEO für ChatGPT und andere generative Suchsysteme transparent messbar.
- Worker / local tools
- 6 / 9
- AI engines
- 5
- Setup time
- ~5 min
- License
- MIT

Über das Produkt
What is mcp-geo?
mcp-geo is an open-source Model Context Protocol (MCP) server for tracking how your brand is cited by AI search assistants. It runs prompts against ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews, then stores raw citations and computed visibility metrics so you can query them from any MCP client.
Run the npm package locally with SQLite for all nine tools, or self-host the six analysis tools on Cloudflare Workers + D1 for scheduled refreshes and remote access. You bring only the engine API keys you want to use.
Built for indie SaaS founders and small marketing teams who want to track AI visibility without paying for a bloated enterprise SEO suite. Read the full README and SETUP.md on GitHub.
Das Ergebnis
Connect mcp-geo to Claude, ask for an AI visibility analysis, and get a strategist-quality memo grounded in per-engine data.
Features
What's inside
Six analysis tools are available on both transports. The local npm CLI also includes brand management and prompt generation tools.
check_visibilityFragen aus deiner Kategorie: Definiere Marke, Kategorie und Wettbewerber, um Fragen zu erzeugen, die deine Kunden einem Assistenten stellen könnten.
get_visibility_historyZitate je Suchsystem: Vergleiche Erwähnungen und Quellen in ChatGPT, Claude, Perplexity, Gemini und Google AI Overviews.
compare_competitorsDaten unter deiner Kontrolle: Hoste das MCP auf Cloudflare Workers und hinterlege nur die API-Schlüssel der Suchsysteme, die du wirklich nutzt.
get_citationsThe actual citation events with prompt, engine, excerpt, type, and brand URL.
get_content_gapsPrioritized content recommendations targeting your losing prompts.
refresh_brandManually trigger a fresh scan across every engine whose API key is set.
Systeme
Systeme
- ChatGPT
- Claude
- Perplexity
- Gemini
- Google AI Overviews
Each engine is opt-in. Configure only the keys you have; the Worker skips engines without credentials.
Einrichtung
Run it locally or connect Claude
The local CLI keeps its SQLite data on your machine. The Worker transport supports remote MCP clients through OAuth.
Lokal ausführen
claude mcp add --transport stdio digestseo -s user --env OPENAI_API_KEY=your_key_here -- npx -y digestseo-mcpWorker verbinden
- In Claude.ai, open Settings → Connectors → Add custom connector.
- Paste your Worker URL after deploy (ending in /mcp).
- Complete the OAuth handshake and ask Claude to check an AI visibility report.
claude mcp add --transport http digestseo https://YOUR-WORKER.YOUR-SUBDOMAIN.workers.dev/mcpBereitstellung
5-minute self-host on Cloudflare
git clone https://github.com/AKzar1el/mcp-geo.git
cd mcp-geo
npm install
npx wrangler login
cp wrangler.example.jsonc wrangler.jsonc
npx wrangler d1 migrations apply digestseo-db --remote
npx wrangler deployDigestSEO-Workspace
Bewahre deine Audits an einem Ort auf.
Erstelle ein kostenloses Konto, um den DigestSEO-Workspace zu testen und Site-Audit-Projekte zu speichern. Für KI-Sichtbarkeit hostest du mcp-geo selbst auf Cloudflare.
Star the repo. Self-host in 5 minutes.
MIT licensed. 5 AI engines. Native MCP integration.
