GEOScore MCP Server
Enables scanning websites for AI search readiness, generating fixes like llms.txt, and comparing GEO scores across domains.
README
GEOScore MCP Server
An MCP server for GEOScore - the AI search optimization platform. Scan any website for GEO (Generative Engine Optimization) readiness and get actionable fixes.
GEO = making your website visible to AI search engines like ChatGPT, Perplexity, Claude, and Gemini.
What is GEO?
GEO (Generative Engine Optimization) is the practice of optimizing websites to be discovered and cited by AI search engines like ChatGPT, Perplexity, and Claude.
Features
Tools (8 tools)
| Tool | Description | Auth Required |
|---|---|---|
geo_scan |
Scan a domain for AI search readiness (score, grade, 11 checks) | No |
geo_deep_scan |
Full pro analysis with implementation report | API Key (Pro) |
geo_generate_fix |
Generate fix code (llms.txt, schema, meta, robots, sitemap) | API Key |
geo_get_profile |
Get domain score history and profile | No |
geo_compare |
Compare two domains side by side | No |
geo_check_visibility |
Check AI search engine citations | API Key (Pro) |
geo_get_report |
Retrieve a saved scan report | No |
geo_create_api_key |
Create a free API key | No |
Resources
geoscore://guides/what-is-geo- Introduction to GEOgeoscore://guides/llms-txt- How to create llms.txtgeoscore://guides/schema-for-ai- Schema.org for AI searchgeoscore://guides/robots-for-ai- robots.txt for AI crawlers
Prompts
geo-optimize- Complete scan -> analyze -> fix -> apply workflowgeo-audit- Comprehensive GEO audit with prioritized recommendationsgeo-compare- Competitive GEO analysis between two domains
Installation
npm (global)
npm install -g geoscore-mcp
Claude Code
Add to your .mcp.json:
{
"mcpServers": {
"geoscore": {
"command": "npx",
"args": ["-y", "geoscore-mcp"],
"env": {
"GEOSCORE_API_KEY": "your-api-key-here"
}
}
}
}
Cursor
Add to Cursor Settings > MCP Servers:
{
"geoscore": {
"command": "npx",
"args": ["-y", "geoscore-mcp"],
"env": {
"GEOSCORE_API_KEY": "your-api-key-here"
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"geoscore": {
"command": "npx",
"args": ["-y", "geoscore-mcp"]
}
}
}
Getting an API Key
Use the geo_create_api_key tool or visit https://geoscoreai.com/api-keys.
Free keys include 10 scans/day. Pro keys unlock deep scans, fix generation, and visibility checks.
Usage Examples
Quick scan
"Scan example.com for AI search readiness"
-> Agent calls geo_scan
Full optimization workflow
"Optimize my website for AI search engines"
-> Agent uses geo-optimize prompt
-> Scans -> Identifies issues -> Generates fixes -> Applies to project
Competitive analysis
"Compare my GEO score against competitor.com"
-> Agent calls geo_compare
Generate specific fix
"Generate an llms.txt file for my site"
-> Agent calls geo_generate_fix with fix_type="llms_txt"
-> Writes the file to project root
API
Base URL: https://api.geoscoreai.com
Full OpenAPI spec: https://geoscoreai.com/openapi.json
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.