GEO AIMCP

Model Context Protocol

An open protocol standardising how AI applications connect to external tools and data sources, letting assistants query systems directly rather than scraping interfaces.

In full

Introduced by Anthropic in November 2024 and since adopted broadly, MCP defines a client-server interface for exposing resources, tools and prompts to a model. For the SEO industry it matters in two ways: analytics and search platforms increasingly ship MCP servers so practitioners can query their data conversationally, and businesses can expose structured product or availability data to agents through a defined interface instead of relying on page scraping.

Example

An analyst connects a search-data MCP server and asks an assistant to compare last quarter's non-brand clicks by template.

Related terms

Agentic browsing

AI systems that navigate websites on a user's behalf — reading pages, filling forms, comparing options and sometimes completing…

Structured data

Machine-readable annotations on a page, usually Schema.org vocabulary in JSON-LD, that describe entities and make pages eligible for rich…

Product feed

A structured file or API supplying product attributes — id, title, description, price, availability, GTIN, images — to shopping platforms…

AI crawler

An automated agent operated by an AI company to fetch web content for model training, search indexing, or live retrieval when answering a…

Answer engine

A system that responds to a question with a synthesised answer and citations rather than a ranked list of documents — for example…