External resources and tools are made available via the Model Context Protocol as a standardized integration layer.
Use this profile to understand the building block briefly, place it in the model, and switch to the 360° assessment when needed.
Theoretical construct: explains a term, principle, or mental model.
What organizes, connects, or makes decisions possible.
The Model Context Protocol (MCP) is a protocol for letting AI applications access tools, data sources, and prompts in a standardized way. It separates the roles of host, client, and server.
MCP emerged from the need to connect language models to external context and actions without building a bespoke integration for every combination. It follows a lineage of protocols and bounded contexts that make responsibilities and exchange boundaries explicit.
Picture a translator and switchboard: the AI application opens a session, an MCP client speaks the protocol, and a server exposes described tools or resources. Calls cross that boundary and can be checked and constrained there.
The host application provides the AI experience and decides which MCP connections are allowed.
The client mediates protocol messages while the server exposes tools, resources, or prompts.
A structured call passes arguments to an external capability and returns its result.
MCP makes AI applications extensible across many external capabilities while keeping responsibilities, permissions, and integration boundaries visible.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.