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

# mcpcensusbot

> Crawler for The MCP Census, a service for checking MCP servers before install. When a search finds no census hit for a brand, it looks for an off-registry server with GET /.well-known/mcp.json, GET /.well-known/mcp-registry-auth and a DoH lookup for mcp.<domain>; GET only, results cached 7–30 days.

## Dossier

- Kind: Agentic web & MCP registries
- Operator: The MCP Census (https://mcpcensus.com/)
- Documentation: https://mcpcensus.com/bot
- robots.txt tokens: none documented
- Feeds: registry / directory
- Respects robots.txt: Not documented. Bot page gives opt-out by email (info@mcpcensus.com); robots.txt not discussed.
- Verification: No published method
- Labels matched in our logs: mcpcensusbot

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

A user searched the census for something related to us; finding our .well-known MCP manifest gets us recorded as a known server.

## Observed behaviour

- Baseline 2026-10-23 (93-day window): 4 requests on 2 days; first seen 2026-10-22, last seen 2026-10-23; New this week.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://mcpcensus.com/
- https://mcpcensus.com/bot
- https://mcpcensus.com/llms.txt

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