--- title: "AI & Agent Discovery — Australian Wedding Celebrants" description: "A plain-English walkthrough of every way this directory makes itself useful to search engines, LLMs, and autonomous agents — from robots.txt through MCP and..." source: "https://australianweddingcelebrants.com.au/ai/" markdown: "https://australianweddingcelebrants.com.au/ai.md" author: "Frankie" --- [View this page as HTML]() AI & agent discovery # How this site works with AI, search engines, and bots A plain-English walkthrough of every machine-readable surface this directory publishes — why it's there, who it helps, and a link to the live endpoint so you can inspect it yourself. By [Frankie]() ## If you're a couple planning a wedding Ask your AI assistant — ChatGPT, Claude, Perplexity, a dedicated wedding planner bot — for celebrant recommendations in Australia. It can read every profile on this site, search by location or specialty, and even email a shortlisted celebrant on your behalf through our relay. You stay in control: the celebrant replies to your email, you take the conversation from there, and we're not involved in the booking. ## If you're a celebrant Being in this directory means your public profile is genuinely visible to the new generation of AI tools couples use to plan. We've built — and maintain — the discovery plumbing (66 celebrants indexed at this build). A directory record does not claim that its subject is currently active or available. Agent-relayed enquiries require an explicit profile opt-in; a missing setting is treated as not opted in. 66 celebrants indexed 0 explicit agent-enquiry opt-ins 16 agent surfaces live 0 commissions taken ## Preferences & signals What this site asks bots to do — and not do. ### Authentication policy (auth.md) [/auth.md →]() This is a public directory: people and agents can browse the site, read the datasets, search through MCP, and use the A2A interface without an account, API key, or OAuth token. The `auth.md` file publishes that anonymous-access policy in one machine-readable place. We intentionally do not publish OAuth or OpenID Connect discovery metadata because this public service does not operate an authorization server or issue access tokens. ### robots.txt with Content Signals [/robots.txt →]() Alongside the standard Allow directives, we publish a Content-Signal line from the[contentsignals.org]() draft:`ai-train=no, search=yes, ai-input=yes`. In plain English: *don't harvest celebrant bios for model training, but please do index us for search and cite us in AI-assisted answers.* That lets couples find celebrants through the AI tools they already use, without turning the directory into free training data. ### Link headers on every page (RFC 8288) Every HTTP response on this site carries `Link` headers pointing at the machine-readable versions of the content — the `service-desc`, `describedby`, `sitemap`, `api-catalog`, `agent-skills`, and `a2a-agent-card` relations. An agent that lands on any page can follow these without scraping to find the structured data. Verify with `curl -sI https://australianweddingcelebrants.com.au/ | grep -i '^link:'` ### Sitemap [/sitemap-index.xml →]() Auto-generated list of every URL on the site, refreshed every build. Useful for Google/Bing and any crawler-style agent doing bulk ingestion. ## Machine-readable content The site content, but in formats an LLM can actually digest. ### llms.txt & llms-full.txt [/llms.txt →]() [/llms-full.txt →]() Following the [llmstxt.org]() convention: a concise text summary of the site (who we are, tier system, all celebrants with tier, location, and URL) plus a full-dump variant that inlines every celebrant's body copy. An LLM that wants broad context in one fetch can read these instead of crawling the HTML. ### Markdown for Agents [/index.md →]() [Sample profile.md →]() Every HTML page has a markdown counterpart. Request any URL on this site with `Accept: text/markdown` and you'll get the markdown version with `Content-Type: text/markdown` and an`X-Markdown-Tokens` estimate — a Cloudflare Pages Function at the edge swaps the response. Browsers still get HTML; agents get the cleaner token-efficient version. Try: `curl -H 'Accept: text/markdown' https://australianweddingcelebrants.com.au/` ### Structured JSON dataset [/directory.json →]() Every profile as typed JSON — slug, tier, profile-listed locations, categories, `australia_wide` / `international` profile flags, contact fields, explicit agent-enquiry opt-in state, credential issuer and verification, provenance, and profile URLs. Updated on every build. This is the backbone that the MCP server and A2A agent both read from. ## Agent discovery A DNS entrypoint and well-known URLs where agents look first to figure out what we offer. ### API catalog (RFC 9727) [/.well-known/api-catalog →]() An `application/linkset+json` document that advertises every machine-readable surface we run — the directory dataset, the MCP endpoint, the A2A endpoint — each with its spec URL and docs. Lets an agent find everything in one GET. ### DNS for AI Discovery (DNS-AID) [Current Internet-Draft →]() Agents can discover the directory before making an HTTP request by resolving `_index._agents.australianweddingcelebrants.com.au`. Its HTTPS ServiceMode record has priority `1`, targets this canonical site, advertises `h2` and `http/1.1` on port `443`, and is authenticated through DNSSEC. DNS-AID is an experimental Internet-Draft rather than a final standard; the HTTPS record format follows RFC 9460. ### MCP Server Card (SEP-1649) [/.well-known/mcp/server-card.json →]() The static discovery card for our MCP server. Advertises the transport (`http`), endpoint URL, and identity. This is how an MCP-capable assistant finds our server without being hard-coded to it. ### Agent Skills index (v0.2.0) [/.well-known/agent-skills/index.json →]() [SKILL.md →]() A published skill (`find-australian-wedding-celebrant`) that teaches any agent how to use this directory well — when to trigger, how to explain tiers, a recommended 5-step flow, and the common pitfalls to avoid. The index is auto-regenerated on every build with a SHA-256 digest so clients can verify they've got the right version. ### A2A Agent Card [/.well-known/agent-card.json →]() The standard [A2A protocol]() card. Names this site as an agent that other agents can delegate to, lists our two skills (`search_celebrants` and `enquire_celebrant`), and publishes the endpoint. ## Live endpoints The services behind the discovery cards. ### MCP server [https://api.australianweddingcelebrants.com.au/mcp →]() A Model Context Protocol server (Streamable HTTP transport, protocol version 2025-06-18) running on our Cloudflare Worker. Exposes five read-only tools: `search_celebrants`, `browse_by_location` (includes celebrants who travel Australia-wide), `browse_by_tier`, `get_celebrant_profile`, and `list_all_celebrants`. Any MCP-capable client — Claude Desktop, Cursor, Zed, a custom agent — can connect and use it. Show a sample call ``` curl -X POST https://api.australianweddingcelebrants.com.au/mcp \ -H 'Content-Type: application/json' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call", "params":{"name":"search_celebrants", "arguments":{"query":"byron bay"}}}' ``` ### A2A agent & enquiry relay [https://api.australianweddingcelebrants.com.au/a2a →]() An Agent-to-Agent endpoint for assistants that want to delegate a task rather than call tools. The headline skill is `enquire_celebrant` for profiles with an explicit opt-in: a couple's planning assistant sends a qualified payload (couple name + email, wedding date, location, at least 30 characters of ceremony notes), we validate and rate-limit, and we email the celebrant with the couple as Reply-To. The celebrant and the couple take it from there — we don't sit in the middle of the conversation. **What we commit to:** no commission, no contract, no interference in the booking. We're a free pass-through for celebrants in the directory. Couples see our disclaimer on every A2A response; celebrants see it in plain English in every enquiry email. A missing opt-in setting blocks the relay; profile owners can change the explicit setting at any time. **Abuse controls:** 10 enquiries per IP per day, 1 per IP per celebrant per day, 30 per celebrant per day across all agents. One "Report spam" click in any enquiry email bans the sender IP for 30 days; three reports against the same agent name permanently block that agent. ### WebMCP (browser-side tools) [/webmcp.js →]() For AI assistants running inside a user's browser (the emerging [WebMCP]() standard, currently in Chrome's early preview). When you load any page on this site, we register five tools with `navigator.modelContext.registerTool` — search, browse by location, browse by tier, view a profile, submit a listing. An in-browser assistant can invoke them directly. Zero-op in browsers that don't support the API. ## Common questions Does this website let AI companies train on celebrant profiles? No. Our robots.txt carries a Content-Signal directive of ai-train=no, which asks compliant crawlers not to use profile statements as training data. We allow search indexing (search=yes) and AI-assisted answers (ai-input=yes) so public directory records can be discovered. Inclusion does not imply that a person is currently active, available, or accepting enquiries. How does an AI assistant actually find a celebrant on this site? We publish a DNS for AI Discovery organisation index, machine-readable versions of every page (llms.txt, directory.json, .md endpoints), and a proper MCP server at api.australianweddingcelebrants.com.au/mcp that an AI agent can call to search, browse by location or tier, and fetch full profiles. We also expose the same capabilities through A2A so one agent can delegate to another. Does an agent need an account, API key, or OAuth token? No. The public directory, machine-readable datasets, MCP search tools, and A2A interface are available anonymously. Agents do not need to register or send credentials. We publish this policy at /auth.md. Validation and rate limits protect against abuse but are not authentication. Can agents email celebrants on behalf of couples? Only when the profile contains an explicit agent-enquiry opt-in. Through the A2A enquire_celebrant skill, the couple's assistant sends a qualified payload (couple name + email, wedding date, location, detailed notes), which is validated and rate-limited before any relay. The directory takes no commission and is not a booking party. Can a celebrant opt out of agent-relayed enquiries? Yes. A profile owner can explicitly enable or disable agent-relayed enquiries through the listing edit flow. A missing setting is treated as not opted in. ## What we don't do Just as important as the list above. - ❌ We don't sell celebrant contact details or directory data to anyone — the dataset is public, and it's public on purpose. - ❌ We don't take a commission, referral fee, or clip from any booking that results from an agent-relayed enquiry. - ❌ We don't consent to AI training on celebrant bios (our `ai-train=no` signal is explicit about this). - ❌ We don't mediate after the first email — the celebrant and the couple talk directly. We're not a booking platform. - ❌ We don't charge celebrants for agent enquiries, higher visibility, or any of this infrastructure. It's free to be listed and free to opt out. ## Optional tools, kept separate This agent-discovery stack was built by Josh Withers. A separate [Tools for celebrants]() page discloses practical workflow, website, SEO, NOIM and business-reading resources connected with Josh. Using or buying any other Josh Withers service has no effect on directory inclusion, endorsement, tier, search visibility or position. Rankings and tiers cannot be bought. [View optional tools]() Questions, suggestions, or want to see another agent surface added? [Get in touch]() [Browse the directory]() [Add your listing]() ## Publisher and corrections Responsible publisher: [Withers XYZ Pty Ltd as trustee for the Snow Withers Trust](), ABN 37 709 073 991.[Request a correction or profile update]()— no sign-in required.