The XML sitemap was invented in 2005. It lists URLs. But as we move towards Agentic AI, the concept of a “page” (URL) helps human navigation, but constrains agent navigation. Agents want actions.

The API Sitemap

We propose a new standard: the API Sitemap. Instead of listing URLs for human consumption, this file lists API endpoints available for agent interaction.

<url>
  <loc>https://api.mcp-seo.com/v1/check-rank</loc>
  <lastmod>2026-01-01</lastmod>
  <changefreq>daily</changefreq>
  <rel>action</rel>
  <openapi_spec>https://mcp-seo.com/openapi.yaml</openapi_spec>
</url>

This allows an agent to discover capabilities rather than just content.

  • Old Way: Index a page about “Mortgage Calculator.” Agent reads it.
  • New Way: Index the Calculator Endpoint. Agent uses it.

Capabilities Discovery

This aligns with the goals of the Model Context Protocol (MCP), facilitating direct action. Search engines will evolve into “Action Engines.” If your sitemap only lists reading material, you will be left behind by competitors who list tools.

The “Actions” Protocol

The industry is moving towards actions.json or OpenAI’s plugin-manifest. These files effectively replace the sitemap for agents. Instead of “Here is a page to read,” they say “Here is a function to call.”

The SEO Pivot: Optimizing functions is the new detailed technical SEO.

  • Function Name: get_stock_price (Clear).
  • Function Name: func1 (Opaque). Clear function naming conventions act as keywords for the “Action Search Engine.”

Glossary of Terms

  • Agentic Web: The specialized layer of the internet optimized for autonomous agents rather than human browsers.
  • RAG (Retrieval-Augmented Generation): The process where an LLM retrieves external data to ground its response.
  • Vector Database: A database that stores data as high-dimensional vectors, enabling semantic search.
  • Grounding: The act of connecting an AI’s generation to a verifiable source of truth to prevent hallucination.
  • Zero-Shot: The ability of a model to perform a task without seeing any examples.
  • Token: The basic unit of text for an LLM (roughly 0.75 words).
  • Inference Cost: The computational expense required to generate a response.