Verityscore Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Verityscore Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP (Model Context Protocol) server for Verity Score — the Shopify-first GEO audit platform.
| 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 |
Add to your Claude Desktop or MCP client config:
{
"mcpServers": {
"verity-score": {
"url": "https://mcp.verityscore.io/mcp"
}
}
}npx @verityscore/mcp-serverThe server starts on http://localhost:3100/mcp.
# 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}'@modelcontextprotocol/sdk v1.xget_geo_scoreReturns 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_readinessReal-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_recommendationsReturns top 3 actionable fixes sorted by revenue impact.
Input: { "domain": "mybrand.com" }
Output: { "totalIssues": 42, "topRecommendations": [{ "priority": 1, "title": "...", "fix": "..." }] }explain_topicExpert 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_infoChecklists and benchmarks for 15 e-commerce verticals. Without argument, lists all verticals.
Input: { "vertical": "beauty" }
Output: { "checklist": { "requiredContent": [...], "expectedTrust": [...] }, "benchmarks": {...} }MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.