neuronto.com agentic web readiness

A+ Manifest validity: 86% (6/7 valid, 3 errors, 8 warnings) · Surface score 62 (coverage 40 + breadth 12 + conformance 10). 6 standards observed across 4 of 9 steps; 7 manifests present, 3 errors, 8 warnings. Checked 2026-10-23 16:04:36 UTC. This grades the agent-facing files published at neuronto.com, not the organisation's products.

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

Coverage by step

01 DiscoverARD, AI Catalog well-known file, RFC 9727 02 Identifynothing observed 03 Permit 04 Readllms.txt 05 Actnothing observed 06 CoordinateA2A 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	valid
AI Catalog well-known file `/.well-known/ai-catalog.json`	valid
MCP Server Cards (SEP-2127) `/.well-known/mcp/server-card.json`	errors	$schema missing (required: https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json) name must be reverse-DNS with exactly one slash, e.g. com.example/weather version missing Content-Type is application/json; SEP-2127 says serve application/mcp-server-card+json description is over 100 characters remotes[0].supportedProtocolVersions missing; clients use it to pick a version before connecting tools/resources/prompts listed in the card; SEP-2127 excludes primitives (list them live, or under a namespaced _meta key) no Access-Control-Allow-Origin: * (required for browser clients) no ETag
Agent2Agent Protocol `/.well-known/agent-card.json`	valid
llms.txt `/llms.txt`	valid	no Markdown links: list the pages an agent should read
AGENTS.md `/AGENTS.md`	absent HTTP 404
Agent Skills `/.well-known/agent-skills/index.json`	absent HTTP 404
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs `/.well-known/api-catalog`	valid
AI Crawler User-Agent Tokens in robots.txt `/robots.txt`	valid	no Content-Signal: line (optional; states ai-train / search / ai-input preferences)
security.txt (RFC 9116) `/.well-known/security.txt`	absent HTTP 404
auth.md `/auth.md`	absent HTTP 404
Open Knowledge Format `/okf/index.md`	absent HTTP 404

What an agent can call

MCP endpoint https://neuronto.com/mcp (streamable-http), tools: find_resource, find_tool, publish_resource, registry_stats — from /.well-known/mcp.json
MCP endpoint https://neuronto.com/mcp (streamable-http), tools: find_resource, find_tool, publish_resource, registry_stats — from /.well-known/mcp/server-card.json
A2A agent Neuronto ARD Registry at https://neuronto.com/a2a, skills: Find an agentic resource, Find a specific tool, Registry statistics
A2A agent Neuronto ARD Registry at https://neuronto.com/a2a, skills: Find an agentic resource, Find a specific tool, Registry statistics
API description https://neuronto.com/openapi.json (application/json)
API description https://neuronto.com/apis.json (application/json)
API description https://neuronto.com/api-docs (text/html)
API description https://neuronto.com/connect (text/html)
API description https://neuronto.com/llms.txt (text/plain)
API description https://neuronto.com/.well-known/ard.json (application/json)
llms.txt: Neuronto, 0 links
robots.txt AI policy: unlisted crawlers allowed; Agentmap https://neuronto.com/.well-known/ard.json

Standards observed

Agent2Agent Protocol https://neuronto.com/.well-known/agent-card.json
llms.txt https://neuronto.com/llms.txt
Agentic Resource Discovery https://neuronto.com/.well-known/ard.json
AI Catalog well-known file https://neuronto.com/.well-known/ai-catalog.json
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://neuronto.com/.well-known/api-catalog
AI Crawler User-Agent Tokens in robots.txt

Cheapest next steps

AGENTS.md: instructions for coding agents working on or with the site
security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people

Agent pre-flight & practical readiness

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

Fetch: POST https://neuronto.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, tables 4 (48 rows), first content at byte 50390, JSON-LD Organization, WebSite, SearchAction, EntryPoint, WebAPI, SoftwareApplication, Offer, FAQPage, Question, Answer.

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

Readiness subscores: reach 20/20, readability 22/30, capabilities 33/35, conformance 10/15, total 85/100, 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