agenticweb.wiki

monday.com agentic web readiness

A+ Manifest validity: 100% (5/5 valid, 0 errors, 4 warnings) · Surface score 80 (coverage 50 + breadth 15 + conformance 15). 7 standards observed across 5 of 9 steps; 5 manifests present, 0 errors, 4 warnings. Checked 2026-10-25 03:15:44 UTC. This grades the agent-facing files published at monday.com, not the organisation's products.

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

Coverage by step

01 DiscoverRFC 972702 Identifynothing observed03 PermitContent Signals Policy, AI Crawler User-Agent Tokens in robots.txt, OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization)04 Readllms.txt05 ActAgent Skills06 CoordinateA2A07 Paynothing observed08 Presentnothing observed

Manifests

ManifestResultFindings
Agentic Resource Discovery
/.well-known/ard.json		absent HTTP 404
AI Catalog well-known file
/.well-known/ai-catalog.json		absent HTTP 404
MCP Server Cards (SEP-2127)
/mcp/server-card		timeout
  • not fetched: timeout
Agent2Agent Protocol
/.well-known/agent-card.json		valid
  • supportedInterfaces missing; A2A 1.0 cards declare interfaces there (url, protocolBinding, protocolVersion) and the top-level url is the 0.3 shape
  • protocolVersion missing; clients cannot tell which A2A revision the card follows
llms.txt
/llms.txt		valid
AGENTS.md
/AGENTS.md		absent HTTP 404
Agent Skills
/.well-known/agent-skills/index.json		valid
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 Agentmap: line (optional convention pointing agents at /.well-known/ard.json)
security.txt (RFC 9116)
/.well-known/security.txt		absent HTTP 404
auth.md
/auth.md		absent HTTP 404
Open Knowledge Format
/okf/index.md		timeout
  • not fetched: timeout

What an agent can call

Standards observed

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

Monday and what it offers to agents

## Read the data, not the HTML
- Index: https://monday.com/llms.txt
- API description: https://monday.com/openapi.json
- Discovery catalog: https://monday.com/.well-known/ard.json

## Calling
- MCP server (Streamable HTTP): https://monday.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@monday.com
  3. security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people
    Generate starter /.well-known/security.txt for monday.com
    Contact: mailto:security@monday.com
Expires: 2027-09-20T23:42:41Z
Canonical: https://monday.com/.well-known/security.txt
Preferred-Languages: en
Policy: https://monday.com/security-policy

Agent pre-flight & practical readiness

Preferred mode: a2a (fallback agent_skills). Send the task to the A2A agent endpoint named in the card. Use the card's skills instead of crawling pages.

Fetch: POST https://mcp.monday.com/mcp Send an A2A message to this agent endpoint. The card lists the skills.

Practical readability: exa_parsable yes, markdown negotiation no, render none, HTML quality none.

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

Readiness subscores: reach 20/20, readability 10/30, capabilities 17/35, conformance 15/15, total 62/100, 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