---
schema_version: "newruntime-reader-dossiers-v1"
type: "reader_dossier"
slug: "agenstrybot"
kind: "agentic_registry"
operator: "Agenstry"
researched_at: "2026-10-23"
confidence: "high"
json_url: "https://newruntime.com/readers/agenstrybot.json"
canonical_url: "https://newruntime.com/readers/agenstrybot/"
---

# AgenstryBot

> Crawler for Agenstry, an AI agent directory for A2A and MCP that publishes measured evidence about public agent infrastructure. It fetches .well-known A2A cards and MCP manifests, sitemaps and metadata, may send a JSON-RPC ping or MCP initialize/tools/list, and rechecks live agents roughly hourly.

## Dossier

- Kind: Agentic web & MCP registries
- Operator: Agenstry (https://agenstry.com/)
- Documentation: https://agenstry.com/bot
- robots.txt tokens: AgenstryBot
- Feeds: registry / directory, monitoring
- Respects robots.txt: Yes, per its documentation. Docs: honors Allow/Disallow/Crawl-delay for AgenstryBot, caches rules up to 1h, backs off on 429/503; blocking stops fresh evidence but keeps the listing. Requests are signed with Web Bot Auth (RFC 9421, Ed25519, Signature-Agent https://agenstry.com) from one GCP europe-west1 host; listed by Cloudflare as a verified bot.
- Verification: Signed requests (Web Bot Auth) (https://agenstry.com/.well-known/http-message-signatures-directory)
- Labels matched in our logs: agenstrybot

## Why it matters to New Runtime (our interpretation)

Signed (Web Bot Auth) registry crawler whose directory also feeds other catalogs such as agent-tools.cloud; its probes are monitor traffic, not usage.

## Observed behaviour

- Baseline 2026-10-23 (93-day window): 73 requests on 9 days; first seen 2026-10-04, last seen 2026-10-22; Returning.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://agenstry.com/
- https://agenstry.com/bot
- https://agent-tools.cloud/about

Identity: A family name is what a client claims in its user agent. It is verified only when its request came from the operator's published IP ranges or passed forward-confirmed reverse DNS, as reported per family in /crawler-journeys.json. Anyone can claim any name.

All dossiers: https://newruntime.com/readers.md