Verity Score MCP server

• Addresshttps://mcp.verityscore.io/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on verityscore.io when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-27
• Tools5
• Server calls itselfio.verityscore/geo-audit
• Server version1.0.2
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 445 ms.

• Its tools do none of the product's use cases we checked: Track the questions shoppers ask AI assistants over time; Check how AI assistants describe and recommend specific products; Generate missing product articles from real store data.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score69 of 100answers 100 · does the job 0 · definitions 100 · context 100 · use 37 · connects 100
• What an agent can do with it0 of 3 use cases
• Use69 npm downloads a week
• Answered100% of days9 of 9 daily checks
• Median first answer483 ms
• Space in an agent's context≈ 591 tokensthe definitions of all its tools (5), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• get_geo_score

  Get the GEO readiness score for a Shopify store. Returns score, vertical, top findings, and report link. If not yet audited, the store is queued for audit within 72 hours.

• check_ai_readiness

  Quick AI readiness check for any website. Checks 5 AI discovery files in real-time: robots.txt, llms.txt, ai.txt, agent-card.json, sitemap.xml. Returns a score from 0 to 5 with per-file recommendations.

• get_recommendations

  Get the top 3 priority recommendations to improve AI visibility for a Shopify store. Returns actionable fixes with expected impact. If not yet audited, the store is queued for audit within 72 hours.

• explain_topic

  Explains a GEO or AI commerce concept with actionable guidance for Shopify merchants. Topics: schema.org, robots.txt, llms.txt, AggregateRating, ACP, UCP, Perplexity Shopping, ChatGPT Shopping, claims, E-E-A-T, and more.

• get_vertical_info

  Get AI commerce checklist and benchmarks for a specific e-commerce vertical (beauty, fashion, food, electronics, etc.). Without argument, lists all 15 supported verticals.

• io.verityscore/geo-auditnot asked yetverified in the MCP registry