pickrate.io publishes an Agentic Resource Discovery manifest at /.well-known/ai-catalog.json, declaring what an AI agent can call on this domain. Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| How Pickrate worksanswers in 695ms The mechanism in plain english: why client-side JavaScript can't observe AI agents at all, the exact payload the server-side collector sends and the fields it never sends (no IP, no raw user-agent, no query strings), how agent-requested-but-missing content ... endpoint: https://pickrate.io/how-it-works.mdidentifier: urn:air:pickrate.io:docs:how-it-workspublished to be found for: how does AI agent attribution work · what data does the Pickrate collector send · can you track conversions from ChatGPT with no referrer how-it-works attribution privacy collector methodology confidence explainer | text/markdown |
| Install guides — measure AI agent trafficanswers in 484ms How to see which AI agents read a site, per hosting platform: Vercel log drain, Cloudflare Worker in front of any origin, Next.js middleware, Mintlify and other hosted docs. Explains why client-side analytics can't see agent traffic at all, and which platfo... endpoint: https://pickrate.io/install.mdidentifier: urn:air:pickrate.io:install:guidespublished to be found for: how do I see which AI agents crawl my site · track ChatGPT and Claude crawlers on Vercel · is GPTBot reading my documentation install analytics crawlers vercel cloudflare mintlify nextjs install-guide | text/markdown |
| Register with Pickrate (auth.md)answers in 483ms auth.md agent-registration skill. Create a Pickrate workspace on behalf of your user with no signup form: register anonymously (write-only until claimed), with the user's email, or with a provider-signed ID-JAG. Then mint a collector key and install tracking. endpoint: https://pickrate.io/auth.mdidentifier: urn:air:pickrate.io:auth:registrationpublished to be found for: sign me up for Pickrate · create a Pickrate account for my user · register for analytics without a signup form auth.md registration oauth signup agent-auth register claim token-exchange | text/markdown |
| Set up Pickrateanswers in 658ms Agent-executable setup prompt. Fetch it and follow it to install Pickrate on the current project — the server-side collector (agent traffic → Pickrate) and the MCP connection — without a human. endpoint: https://pickrate.io/setup.mdidentifier: urn:air:pickrate.io:setup:promptpublished to be found for: set up Pickrate on this project · install Pickrate agent analytics · connect Pickrate to my agent setup install onboarding collector mcp self-install | text/markdown |
| Pickrate MCP Servernot yet checked Pickrate's read tools over MCP (Streamable HTTP): Pick Rate, leaderboards, reports. identifier: urn:air:pickrate.io:mcp:pickratepublished to be found for: what is the pick rate of Stripe · best work management tool for AI agents · which database do coding agents pick mcp pick-rate measurement getPickRate getLeaderboard lookupTool | application/mcp-server-card+json |
| Pickrate Agent Registryanswers in 291ms ARD registry of developer & SaaS tools. Search by task; results carry each tool's Pick Rate (how often agents pick it). endpoint: https://pickrate.io/api/ard/searchidentifier: urn:air:pickrate.io:registry:publicpublished to be found for: an issue tracker my agent can drive · vector database for a RAG app · transactional email API registry ard pick-rate search explore agents | application/ai-registry+json |
https://pickrate.io/.well-known/ai-catalog.json, this publisher's own file. Identifiers are reproduced exactly as published.
Note: this is the pre-v0.91 path. The specification renamed the manifest to /.well-known/ard.json, and most of the ecosystem still serves the older name.
Of the resources listed, 5 have been probed for reachability.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.