See how AI agents read this website

Step 1

Markdown instead of HTML

When an AI agent asks for a page with the header Accept: text/markdown, this site replies with a clean Markdown version instead of HTML. The agent gets the same content in a fraction of the tokens, with no menus, styling, or scripts to wade through.

• Every page has a Markdown twin, such as /pricing/index.md
• An x-markdown-tokens header tells the agent how long it is
• Regular visitors and search engines still get the normal page

Choose a page and press "Fetch as Markdown".

Step 2

Discovery files and Link headers

Agents need to know what a site offers before they start. Every page sends standard Link headers (RFC 8288) that point to the site's machine-readable files.

• llms.txt: a plain-language summary with links to every key page
• robots.txt: crawl rules plus Content Signals (search yes, AI answers yes, AI training no)
• MCP server card and API catalog: how to connect programmatically

Press the button to read the live Link header.

Step 3

An MCP server agents can talk to

The Model Context Protocol is how AI assistants connect to outside tools. This site runs a small, read-only MCP server at /mcp. An assistant can ask it about services, pricing, service areas and FAQs, or search the site, and get answers straight from the source.

• Read-only: it can't change anything or send messages
• Uses the standard JSON-RPC messages any MCP client sends

Request

Pick an action above.

Response

…

Step 4

WebMCP: tools inside the browser

WebMCP is a new browser feature that lets a page offer tools directly to an AI agent running in your browser. Instead of guessing which buttons to click, the agent sees named actions with clear inputs.

• Read-only tools: business info, services, pricing, page content
• open_page to navigate the site
• request_consultation: the contact form, which the agent fills in and you send

• get_business_info
• list_services
• get_pricing
• get_page_content
• open_page

Checking whether your browser supports WebMCP…

Step 5

Structured data search engines and agents trust

Behind every page is structured data (schema.org JSON-LD) that states facts precisely: the business, its location and service area, its services and prices, and its FAQs. Search engines use it for rich results, and agents use it to confirm they have the right business.

Choose a page to see its schema types.