---
schema_version: "newruntime-reader-dossiers-v1"
type: "reader_dossier"
slug: "agent-tools-cloud-crawler"
kind: "agentic_registry"
operator: "agent-tools.cloud"
researched_at: "2026-10-23"
confidence: "medium"
json_url: "https://newruntime.com/readers/agent-tools-cloud-crawler.json"
canonical_url: "https://newruntime.com/readers/agent-tools-cloud-crawler/"
---

# agent-tools.cloud crawler

> Crawler for agent-tools.cloud, an open discovery directory of x402 paid APIs, remote MCP servers and A2A agents. Per its about page it runs initialize + tools/list conformance checks on MCP servers, fetches and parses A2A agent cards, and re-probes availability daily.

## Dossier

- Kind: Agentic web & MCP registries
- Operator: agent-tools.cloud (https://agent-tools.cloud/)
- Documentation: none found
- robots.txt tokens: none documented
- Feeds: registry / directory, monitoring
- Respects robots.txt: Not documented. About page does not mention robots.txt or the crawler UA; attribution rests on the domain embedded in the UA name.
- Verification: No published method
- Labels matched in our logs: agent-tools.cloud-crawler

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

Listing in an x402/MCP/A2A discovery directory with health grades is a direct path for agents to find our MCP and paid endpoints.

## Observed behaviour

- Baseline 2026-10-23 (93-day window): 395 requests on 26 days; first seen 2026-09-25, last seen 2026-10-22; Regular.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://agent-tools.cloud/
- https://agent-tools.cloud/about
- https://mcp.so/server/agent-tools-mcp/AgentTools-Cloud

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