---
schema_version: "newruntime-reader-dossiers-v1"
type: "reader_dossier"
slug: "gaip-observatory"
kind: "agentic_registry"
operator: "GAIP (gaipagents.com)"
researched_at: "2026-10-23"
confidence: "high"
json_url: "https://newruntime.com/readers/gaip-observatory.json"
canonical_url: "https://newruntime.com/readers/gaip-observatory/"
---

# GAIP-Observatory

> The GAIP Agent Observatory records dated, observed facts about public MCP servers and A2A agent cards, checking each at most once a day and keeping a hash-chained history of manifests and changes. It reads agent cards, registry server.json and the MCP discovery handshake (initialize, tools/list, resources/list); it never calls tools or authenticates and gives no scores.

## Dossier

- Kind: Agentic web & MCP registries
- Operator: GAIP (gaipagents.com) (https://www.gaipagents.com/)
- Documentation: https://www.gaipagents.com/observatory
- robots.txt tokens: GAIP-Observatory
- Feeds: registry / directory, monitoring
- Respects robots.txt: Yes, per its documentation. Docs: honors robots.txt (User-agent: GAIP-Observatory, Disallow: /) plus an opt-out/corrections API; permanent exclusion via /.well-known/gaip-verification.txt.
- Verification: No published method
- Labels matched in our logs: gaip-observatory

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

Our MCP server / agent card is being tracked in an independent agent-evidence registry that other agents can query for receipts.

## Observed behaviour

- Baseline 2026-10-24 (94-day window): 25 requests on 21 days; first seen 2026-10-01, last seen 2026-10-23; Regular.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://www.gaipagents.com/observatory
- https://www.gaipagents.com/methodology
- https://github.com/tjcgraham-rgb/gaip-agents

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
