@verityscore/mcp-server
Enables GEO auditing and optimization for Shopify stores, including GEO score, AI readiness checks, and actionable recommendations.
README
@verityscore/mcp-server
MCP (Model Context Protocol) server for Verity Score — the Shopify-first GEO audit platform.
5 Tools
| Tool | Description |
|---|---|
get_geo_score |
GEO readiness score for a Shopify store (8 dimensions, top findings, report link) |
check_ai_readiness |
Real-time check of 5 AI discovery files (robots.txt, llms.txt, ai.txt, agent-card.json, sitemap.xml) |
get_recommendations |
Top 3 priority fixes with estimated revenue impact |
explain_topic |
Expert guides on 19 GEO & AI commerce topics |
get_vertical_info |
Checklists & benchmarks for 15 e-commerce verticals |
Quick Start
Use the hosted server (recommended)
Add to your Claude Desktop or MCP client config:
{
"mcpServers": {
"verity-score": {
"url": "https://mcp.verityscore.io/mcp"
}
}
}
Run locally
npx @verityscore/mcp-server
The server starts on http://localhost:3100/mcp.
Test with curl
# List all tools
curl -X POST http://localhost:3100/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
# Check AI readiness of any site
curl -X POST http://localhost:3100/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"check_ai_readiness","arguments":{"domain":"mybrand.com"}},"id":2}'
Architecture
- Transport: Streamable HTTP (stateless)
- Auth: None (rate-limited to 10 req/min/IP)
- Protocol: MCP v2025-03-26
- SDK:
@modelcontextprotocol/sdkv1.x
Tools Detail
get_geo_score
Returns the GEO audit score for a Shopify store. If the store has been audited, returns scores across 8 dimensions + top 5 issues. If not yet audited, queues it for analysis within 72 hours.
Input: { "domain": "mybrand.com" }
Output: { "status": "audited", "scores": [...], "topIssues": [...], "reportUrl": "..." }
check_ai_readiness
Real-time check of 5 AI discovery files. No database needed — fetches files directly from the target domain.
Input: { "domain": "mybrand.com" }
Output: { "score": 3, "maxScore": 5, "checks": [...], "recommendation": "..." }
get_recommendations
Returns top 3 actionable fixes sorted by revenue impact.
Input: { "domain": "mybrand.com" }
Output: { "totalIssues": 42, "topRecommendations": [{ "priority": 1, "title": "...", "fix": "..." }] }
explain_topic
Expert knowledge base covering 19 GEO topics. Fuzzy-matches by slug, tag, or title.
Input: { "topic": "schema.org" }
Output: { "title": "Schema.org Product: Why and How", "keyPoints": [...], "readMore": {...} }
get_vertical_info
Checklists and benchmarks for 15 e-commerce verticals. Without argument, lists all verticals.
Input: { "vertical": "beauty" }
Output: { "checklist": { "requiredContent": [...], "expectedTrust": [...] }, "benchmarks": {...} }
Links
- Hosted MCP: https://mcp.verityscore.io/mcp
- Website: https://verityscore.io
- Free Audit: https://verityscore.io/fr/
- Knowledge Base: https://verityscore.io/en/kb/
- Agent Card: https://verityscore.io/.well-known/agent-card.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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.