attio.com agentic web readiness

B Manifest validity: 75% (3/4 valid, 3 errors, 8 warnings) · Surface score 43 (coverage 30 + breadth 3 + conformance 10). 3 standards observed across 3 of 9 steps; 4 manifests present, 3 errors, 8 warnings. Checked 2026-10-25 03:09:05 UTC. This grades the agent-facing files published at attio.com, not the organisation's products.

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

Coverage by step

Manifests

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json",
  "name": "com.attio/attio",
  "title": "Attio",
  "version": "1.0.0",
  "description": "Attio and what it offers to agents",
  "websiteUrl": "https://attio.com/",
  "icons": [
    {
      "src": "https://attio.com/icon.png",
      "mimeType": "image/png",
      "sizes": [
        "180x180"
      ]
    }
  ],
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://attio.com/mcp",
      "supportedProtocolVersions": [
        "2025-11-25",
        "2025-06-18",
        "2025-03-26"
      ]
    }
  ]
}

What an agent can call

• MCP endpoint https://mcp.attio.com (sse) — from /.well-known/mcp.json
• A2A agent Attio at https://attio.com
• llms.txt: Attio, 24 links, llms-full.txt present
• robots.txt AI policy: blocks CCBot, Bytespider, cohere-ai, YouBot; allows GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, anthropic-ai, Google-Extended, PerplexityBot, Applebot-Extended, Amazonbot, DuckAssistBot; unlisted crawlers allowed
• Endpoint check (a2a https://attio.com): pseudo_endpoint_html (agent card url points to the HTML homepage rather than a callable A2A endpoint)

Standards observed

• Agent2Agent Protocol https://attio.com/.well-known/agent-card.json
• llms.txt https://attio.com/llms.txt
• AI Crawler User-Agent Tokens in robots.txt https://attio.com/robots.txt

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": "attio.com"}))
2. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for attio.com

   # Attio for agents
   
   Attio and what it offers to agents
   
   ## Read the data, not the HTML
   - Index: https://attio.com/llms.txt
   - API description: https://attio.com/openapi.json
   - Discovery catalog: https://attio.com/.well-known/ard.json
   
   ## Calling
   - MCP server (Streamable HTTP): https://attio.com/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@attio.com
   

3. api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description (conditional spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "api-catalog-rfc9727", "domain": "attio.com"}))

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback llms_txt). Call the MCP endpoint at https://mcp.attio.com first. Do not scrape the HTML when a tool can answer. Split-brain llms.txt: attio.com/llms.txt has 24 links while docs.attio.com/llms.txt has 369 technical links. Probe docs.attio.com for full developer documentation.

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

Subdomain discovery hint (split_brain_llms_txt): Split-brain llms.txt: attio.com/llms.txt has 24 links while docs.attio.com/llms.txt has 369 technical links. Probe docs.attio.com for full developer documentation. (check docs.attio.com)

Practical readability: exa_parsable yes, markdown negotiation no, render ssr_rich, HTML quality high, first content at byte 79828, HTML-to-llms.txt token ratio 56.717×, JSON-LD Organization, ImageObject, WebSite, SoftwareApplication, Offer.

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

Readiness subscores: reach 16/20, readability 22/30, capabilities 16/35, conformance 10/15, total 64/100, grade B.

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