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

# BrickBlueBot

> Crawler for brick.blue's registry of agents and tools. It reads DNS TXT (_agent/_mcp), .well-known agent/MCP cards, llms.txt, openapi.json and agents.json, runs MCP initialize and tools/list (plus up to three no-argument tools/call on read-only-looking tools), and reads x402 402 responses without paying.

## Dossier

- Kind: Agentic web & MCP registries
- Operator: brick.blue (https://brick.blue/)
- Documentation: https://brick.blue/bot
- robots.txt tokens: BrickBlueBot
- Feeds: registry / directory
- Respects robots.txt: Partly, per its documentation. Docs: robots.txt governs content fetches (llms.txt, openapi.json, pages) but not discovery documents (.well-known files, agent cards, MCP handshake).
- Verification: No published method
- Labels matched in our logs: brickbluebot

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

It indexes exactly the discovery surfaces New Runtime publishes (.well-known, llms.txt, /mcp/) into a hireable agent registry, and may invoke read-only tools.

## Observed behaviour

- Baseline 2026-10-23 (93-day window): 355 requests on 20 days; first seen 2026-09-26, last seen 2026-10-23; Regular.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://brick.blue/
- https://brick.blue/bot
- https://apis.io/providers/brick-blue/

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