AXRAY MCP server

• Addresshttps://axray.online/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on axray.online 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
• Tools4
• Server calls itselfaxray
• Server version1.5.7
• Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 580 ms.

• Its tools do check what AI assistants see on a website, but not find which customer questions a site cannot answer.

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 score82 of 100answers 100 · does the job 50 · definitions 83 · context 100 · connects 100
• What an agent can do with it1 of 2 use cases
• Answered100% of days7 of 7 daily checks
• Median first answer471 ms
• Space in an agent's context≈ 644 tokensthe definitions of all its tools (4), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once

• Not saying whether it only reads or can destroy: 4 of 4

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 →

• scan_url

  Fetch a URL the way an AI crawler does — one plain HTTP request, no browser, no JavaScript — and score it against the published Agent Experience rubric (70 checks, five pillars, spec v1.5.7). Returns a score out of 100, a grade, the…

• explain_check

  Return the definition of a single Agent Experience check: which pillar it belongs to, what it is worth, why an agent cares, and whether it is fixable in configuration rather than code. Use this after scan_url when somebody asks what a…

• list_crawlers

  Return every AI crawler this scanner resolves robots.txt against: its product token, its operator, which category it belongs to, and one sentence on what blocking it actually costs the site. Use this when somebody asks which bots to allow…

• get_index

  Return the public AX Index: the best known Agent Experience score for each host whose owner verified the domain and asked to be listed. Use it to compare a site against published scores. Costs nothing and hits no network.