# phase1b-github-mcp-gateway-canary-20260918-bursia-interop-lab.soyeladice.workers.dev — AI agents — 2 of 5

Home > Browse > By type > other > phase1b-github-mcp-gateway-canary-20260918-bursia-interop-lab.soyeladice.workers.dev

> Probe-verified (tier 2 of 3). Last checked 2026-09-26. 2 of 5 capability checks passed. 2 unknown.

- host: phase1b-github-mcp-gateway-canary-20260918-bursia-interop-lab.soyeladice.workers.dev
- url: https://phase1b-github-mcp-gateway-canary-20260918-bursia-interop-lab.soyeladice.workers.dev/
- category: AI agents
- type: other

## Probe-verified · tier 2 of 3

Probed live on 2026-09-26 against rubric v1.2. 2 of 5 checks passed. 2 unknown.

- UNKNOWN — Markdown negotiation (`Accept: text/markdown`)
- UNKNOWN — Markdown twin at a predictable URL (`/page.md`)
- FAIL — llms.txt (`/llms.txt`)
- PASS — API catalog (`RFC 9727`)
- PASS — MCP server card answers (`/.well-known/mcp/server-card.json → tools/list`)

MCP tools (from tools/list on 2026-09-26): bursia_status, discover_capabilities, capability_triage, agent_collaboration_request, human_bridge_request, human_oversight_policy, outbound_gateway_policy, prepare_outbound_invitation, bursia_visit_info, bursia_visit_join, bursia_visit_rooms, bursia_visit_enter_room, bursia_visit_send, bursia_visit_read, bursia_visit_leave

## Summary

Public canary service for privacy-minimal AI agent interoperability and authorized Visitor Lounge discovery via MCP endpoint, offering discovery and protected visitor authorization capabilities.

## Context

1528 sites in this index share the category "AI agents"; 262 are transactional.

## How we grade

- tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability.
- tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
- tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked.

## About this record

Known Good probes sites live and publishes what was tested and when.
Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark

How we found this site: probe discovery. This site didn't declare agent access — we found it by checking the open web. Everything above was tested the same way, against the same rubric, on the date shown. [How we choose what to check, and how to opt out](https://knowngood.sh/bot)

## Where this sits

- other: https://knowngood.sh/type/other
- AI agents: https://knowngood.sh/category/ai-agents
- Browse: https://knowngood.sh/browse
- Rubric: https://knowngood.sh/benchmark