MCP defines how an LLM client (a chat app, an agent, an IDE) can request context and invoke tools exposed by a server (a data source, an API, a local script). It was published as an open specification in 2024.
Why it matters for SEO
MCP is emerging as the default way for brands to expose structured, freshest-first content to AI assistants. A brand that publishes an MCP server for its product catalogue, docs, or pricing gives agents a canonical source that bypasses generic web crawls.
Example
A SaaS vendor publishes an MCP server for its docs. Claude, Cursor, and other MCP-compatible clients query the server directly, returning citations to the live docs on every relevant developer question.
How SEM Optimiser reports it
The GEO audit surfaces whether a domain publishes an MCP endpoint and, if so, monitors its uptime and response schema.
Related terms
- llms.txt
llms.txt is a plain-text file at the root of a domain that lists the site's key content and signals to LLM-based crawlers how the content should be discovered and used.
- GEO (Generative Engine Optimisation)
Generative Engine Optimisation is a broader discipline than AEO, covering how content, brand entity, and technical signals influence generation by large language models across all AI surfaces.
- AEO (Answer Engine Optimisation)
Answer Engine Optimisation is the practice of structuring content so it is selected and cited by answer-first engines including ChatGPT, Perplexity, Gemini, and Google's AI Overviews.
- Structured Data
Structured data is standardised, machine-readable markup embedded in a web page that describes its content to search engines and other consumers.