loops.so agentic web readiness

A+ Manifest validity: 71% (5/7 valid, 2 errors, 11 warnings) · Surface score 60 (coverage 40 + breadth 15 + conformance 5). 8 standards observed across 4 of 9 steps; 7 manifests present, 2 errors, 11 warnings. Checked 2026-10-23 16:11:34 UTC. This grades the agent-facing files published at loops.so, not the organisation's products.

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

Coverage by step

01 DiscoverAI Catalog well-known file 02 Identifynothing observed 03 PermitOAuth Protected Resource and Authorization Server Metadata (as used for agent authorization), CIMD 04 Readllms.txt, Markdown for Agents 05 ActAgent Skills 06 Coordinatenothing observed 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	absent HTTP 404
AI Catalog well-known file `/.well-known/ai-catalog.json`	valid	no entry has representativeQueries; ARD registries use 2-5 example queries to index entries
MCP Server Cards (SEP-2127) `/.well-known/mcp/server-card.json`	valid	Content-Type is application/json;charset=utf-8; SEP-2127 says serve application/mcp-server-card+json remotes[0].supportedProtocolVersions missing; clients use it to pick a version before connecting no Access-Control-Allow-Origin: * (required for browser clients)
Agent2Agent Protocol `/.well-known/agent-card.json`	absent HTTP 404
llms.txt `/llms.txt`	valid
AGENTS.md `/AGENTS.md`	absent HTTP 404
Agent Skills `/.well-known/agent-skills/index.json`	valid	skills[0].digest missing skills[1].digest missing skills[2].digest missing skills[3].digest missing
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs `/.well-known/api-catalog`	errors	Content-Type must be application/linkset+json (RFC 9727 §4), got application/json;charset=utf-8
AI Crawler User-Agent Tokens in robots.txt `/robots.txt`	valid	no AI crawler token named (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, ...); the policy for them is whatever User-agent: * says (partial) no Agentmap: line (optional convention pointing agents at /.well-known/ard.json) 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`	errors	none of the auth.md mechanism names found (identity_assertion, service_auth, anonymous)
Open Knowledge Format `/okf/index.md`	absent HTTP 404

What an agent can call

MCP endpoint https://mcp.loops.so (streamable-http) — from /.well-known/mcp.json
MCP endpoint https://mcp.loops.so (streamable-http) — from /.well-known/mcp/server-card.json
API description https://app.loops.so/openapi.json (application/json)
API description https://loops.so/docs (text/html)
llms.txt: Loops, 151 links
robots.txt AI policy: unlisted crawlers partial
OAuth protected resource https://mcp.loops.so, authorization servers: https://app.loops.so

Standards observed

llms.txt https://loops.so/llms.txt
AI Catalog well-known file https://loops.so/.well-known/ai-catalog.json
OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) https://loops.so/.well-known/oauth-protected-resource
Agent Skills https://loops.so/.well-known/agent-skills/index.json
OAuth Client ID Metadata Document https://loops.so/.well-known/oauth-authorization-server
Markdown for Agents https://loops.so/
MCP Server Cards (SEP-2127)
Model Context Protocol

Cheapest next steps

Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch
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://mcp.loops.so first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://mcp.loops.so 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 yes, render markdown_native, HTML quality high, first content at byte 0.

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

Readiness subscores: reach 19/20, readability 30/30, capabilities 35/35, conformance 5/15, total 89/100, 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