By Faro MCP server

• Addresshttps://byfaro.ai/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on byfaro.ai 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 2026-10-28
• Tools5
• Server calls itselffaro-ai-readiness
• Server version2.0.0
• Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 503 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 5 of the 7 days it takes to judge reliability.

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 scoreafter a weeka score needs 7 daily checks: 5 so far
• Answeredmeasuring5 of the 7 daily checks it takes to print a share
• Median first answer441 ms
• Space in an agent's context≈ 927 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 →

• search_businesses

  Search Faro's Agent Registry for real companies filtered by machine-readable capability: public API documentation, llms.txt, an MCP server, structured pricing, whether they permit AI crawlers, and minimum AI visibility score. Use this…

• find_alternatives

  Given a company domain, return comparable companies with an equal or higher AI visibility score. Use this when a vendor cannot be worked with programmatically and you need a substitute an agent can integrate with, or when comparing…

• get_business_profile

  Look up one domain in Faro's Agent Registry and return its full AI visibility profile: score, grade, every capability flag, and when Faro last verified it. Use this to check whether a specific vendor can be worked with programmatically…

• scan_website

  Run a live AI visibility audit on any website. Returns a score from 0-100, a letter grade (A-F), and a check-by-check breakdown across 7 categories (Agent Permissions, Content Discoverability, Structured Data, Pricing Transparency, Agent…

• get_score_index

  Return the Faro Score Index, a public leaderboard of AI visibility scores for well-known websites, refreshed daily. Use this for benchmarks and category context, not for looking up a specific company — use get_business_profile for that.