AI Agent Access
This page is available as structured data for AI agents. All resources are static files served from Cloudflare's edge network with 24-hour caching.
- MCP Server
- https://directory.selleys.com.au/cleaning/public-mcp
- MCP Manifest
- https://directory.selleys.com.au/cleaning/mcp.json
- Root Directory
- https://directory.selleys.com.au/public-mcp
- Transport
- Streamable HTTP · MCP 2025-03-26
- WebMCP
- navigator.modelContext tools (Chrome 146+)
- Available Formats
-
Direct HTTP Access
Fetch any resource directly with standard HTTP:
curl https://directory.selleys.com.au/cleaning/index.json # Structured data
curl https://directory.selleys.com.au/cleaning/index.jsonld # Schema.org linked data
curl https://directory.selleys.com.au/cleaning/index.md # LLM-friendly text
curl https://directory.selleys.com.au/cleaning/mcp.json # MCP manifest
MCP Client Configuration
Connect your AI agent to this page's MCP server endpoint:
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"directory": {
"type": "http",
"url": "https://directory.selleys.com.au/cleaning/public-mcp"
}
}
}
ChatGPT
In ChatGPT, go to Settings → Connectors → Create and enter:
Name: directory
URL: https://directory.selleys.com.au/cleaning/public-mcp
OpenAI MCP docs →
Gemini
Add to Gemini CLI settings.json:
{
"mcpServers": {
"directory": {
"httpUrl": "https://directory.selleys.com.au/cleaning/public-mcp"
}
}
}
Claude Code
claude mcp add directory \
--transport http https://directory.selleys.com.au/cleaning/public-mcp
How it works
Each page is pre-rendered in multiple formats and published to Cloudflare R2. The MCP server speaks JSON-RPC 2.0 over Streamable HTTP, backed by edge-cached resources from 300+ locations worldwide.
- Protocol
- MCP 2025-03-26 (Streamable HTTP + Legacy SSE)
- Caching
- Workers KV manifests (24h) + edge-cached content (1h)
- Authentication
- None required — public read-only access
