developers.sinch.com agentic web readiness

A Manifest validity: 50% (2/4 valid, 3 errors, 15 warnings) · Surface score 54 (coverage 40 + breadth 9 + conformance 5). 5 standards observed across 4 of 9 steps; 4 manifests present (+ robots.txt), 3 errors, 15 warnings. Checked 2026-10-25 23:40:45 UTC. This grades the agent-facing files published at developers.sinch.com, not the organisation's products.

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

Coverage by step

Manifests

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

{
  "$schema": "https://schemas.agentskills.io/discovery/0.2.0/schema.json",
  "skills": [
    {
      "name": "developers",
      "type": "skill-md",
      "description": "Developers and what it offers to agents",
      "url": "https://developers.sinch.com/.well-known/agent-skills/developers/SKILL.md",
      "digest": "sha256:0000000000000000000000000000000000000000000000000000000000000000"
    }
  ]
}

What an agent can call

• MCP endpoint https://developers.sinch.com/mcp (streamable-http), tools: execute, describe-tools, submit-feedback — from /.well-known/mcp/server-card.json
• A2A agent Developer Documentation at https://developers.sinch.com/a2a
• llms.txt: Sinch Developer Documentation, 239 links
• robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed on public paths (subpaths disallowed under User-agent: *)

Standards observed

• Agent2Agent Protocol https://developers.sinch.com/.well-known/agent-card.json
• llms.txt https://developers.sinch.com/llms.txt
• Agent Skills https://developers.sinch.com/.well-known/agent-skills/index.json
• MCP Server Cards (SEP-2127)
• Model Context Protocol

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

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

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback a2a). Call the MCP endpoint at https://developers.sinch.com/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://developers.sinch.com/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 no, render ssr_rich, HTML quality high, first content at byte 299613 (~293 KB of head/script markup before main text), HTML-to-llms.txt token ratio 4.826×.

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

Readiness subscores: reach 20/20, readability 20/30, capabilities 22/35, conformance 5/15, total 67/100, 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