agora.io agentic web readiness

D Manifest validity: 0% (0/1 valid, 1 error, 6 warnings) · Surface score 15 (coverage 10 + breadth 0 + conformance 5). 1 standard observed across 1 of 9 steps; 1 manifest present (+ robots.txt), 1 error, 6 warnings. Checked 2026-10-25 09:44:28 UTC via www.agora.io. This grades the agent-facing files published at agora.io, not the organisation's products.

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

Coverage by step

Manifests

# Agora

> Agora and what it offers to agents

Short notes an agent should know before using the site: what it is for, who runs it, how to cite it.

## Docs
- [Getting started](https://agora.io/docs/getting-started): the first page to read
- [API reference](https://agora.io/openapi.json): OpenAPI description

## Optional
- [Changelog](https://agora.io/changelog): what changed, newest first

What an agent can call

• llms.txt: untitled, 0 links
• robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed

Standards observed

• Markdown for Agents https://agora.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": "agora.io"}))
2. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for agora.io

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

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": "agora.io"}))

Agent pre-flight & practical readiness

Preferred mode: markdown_negotiation. GET / with Accept: text/markdown. The origin already serves a Markdown body for agents. agora.io publishes no root agent discovery manifests, but docs.agora.io serves /llms.txt (53 links). Probe docs.agora.io or publish /.well-known/ard.json on agora.io to link them.

Fetch: GET https://agora.io/ GET / with Accept: text/markdown. The origin negotiates a Markdown body.

Subdomain discovery hint (subdomain_stranded): agora.io publishes no root agent discovery manifests, but docs.agora.io serves /llms.txt (53 links). Probe docs.agora.io or publish /.well-known/ard.json on agora.io to link them. (check docs.agora.io)

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 2.901×.

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 2/35, conformance 5/15, total 57/100, 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