xata.io agentic web readiness

A+ Manifest validity: 83% (5/6 valid, 1 error, 8 warnings) · Surface score 75 (coverage 50 + breadth 15 + conformance 10). 8 standards observed across 5 of 9 steps; 6 manifests present (+ robots.txt), 1 error, 8 warnings. Checked 2026-10-25 03:20:31 UTC. This grades the agent-facing files published at xata.io, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/xata.io.svg) · JSON · Markdown · Re-check now

Coverage by step

Manifests

{
  "name": "Xata",
  "description": "Xata and what it offers to agents",
  "version": "1.0.0",
  "provider": {
    "organization": "Xata",
    "url": "https://xata.io/"
  },
  "documentationUrl": "https://xata.io/AGENTS.md",
  "supportedInterfaces": [
    {
      "url": "https://xata.io/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    }
  ],
  "url": "https://xata.io/a2a",
  "protocolVersion": "1.0",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "answer",
      "name": "Answer questions",
      "description": "Answer questions about Xata.",
      "tags": [
        "qa"
      ],
      "examples": [
        "What does Xata do?"
      ]
    }
  ],
  "securitySchemes": {},
  "securityRequirements": []
}

What an agent can call

• MCP endpoint https://api.xata.tech/mcp (streamable-http) — from /.well-known/ai-catalog.json#urn:air:xata.io:mcp:xata
• A2A agent Xata at https://xata.io/docs/, skills: branching-postgresql-for-agents, managing-postgresql, using-xata-api, using-xata-cli
• API description https://api.xata.tech/openapi.json (application/vnd.oai.openapi+json)
• API description https://xata.io/docs/index.md (text/markdown)
• API description https://xata.io/docs (text/html)
• API description https://api.xata.tech/.well-known/oauth-protected-resource/mcp (application/json)
• llms.txt: Xata, 50 links, llms-full.txt present
• robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed
• ARD bridge (/.well-known/ai-catalog.json): 1/1 valid, 0 legacy, 0 dead/broken (served at deprecated path only)

Standards observed

• Agent2Agent Protocol https://xata.io/.well-known/agent-card.json
• llms.txt https://xata.io/llms.txt
• Content Signals Policy https://xata.io/robots.txt
• AI Catalog well-known file https://xata.io/.well-known/ai-catalog.json
• api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://xata.io/.well-known/api-catalog
• auth.md https://xata.io/auth.md
• Agent Skills https://xata.io/.well-known/agent-skills/index.json
• Markdown for Agents https://xata.io/

Cheapest next steps

1. Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch (emerging spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "ard", "domain": "xata.io"}))
2. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for xata.io

   # Xata for agents
   
   Xata and what it offers to agents
   
   ## Read the data, not the HTML
   - Index: https://xata.io/llms.txt
   - API description: https://xata.io/openapi.json
   - Discovery catalog: https://xata.io/.well-known/ard.json
   
   ## Calling
   - MCP server (Streamable HTTP): https://xata.io/mcp
   - Rate limits and authentication: describe them here
   
   ## Conventions
   - How to cite or attribute content
   - What not to do (no scraping of /account/, no automated sign-ups, etc.)
   
   Contact: security@xata.io
   

3. security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people
   Generate starter /.well-known/security.txt for xata.io

   Contact: mailto:security@xata.io
   Expires: 2027-09-20T23:45:08Z
   Canonical: https://xata.io/.well-known/security.txt
   Preferred-Languages: en
   Policy: https://xata.io/security-policy
   

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback openapi). Call the MCP endpoint at https://api.xata.tech/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://api.xata.tech/mcp POST a JSON-RPC tools/list, or server/discover on the 2026-07-28 revision, before reading HTML.

Practical readability: exa_parsable yes, markdown negotiation yes, render markdown_native, HTML quality high, first content at byte 0, HTML-to-llms.txt token ratio 1.214×.

AI crawler posture: open_to_all · Assistant access: OpenAI allowed, Anthropic allowed, Google allowed, Perplexity allowed, Exa allowed.

Readiness subscores: reach 20/20, readability 30/30, capabilities 35/35, conformance 10/15, total 95/100, grade A+.

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules