AI engineering glossary · Agents tools MCP
What is MCP sampling?
MCP sampling: An MCP feature that lets a server ask the client's language model to generate text on its behalf, so the server does not need its own model access. The client stays in control and can require user approval before allowing it.
MCP sampling: an example
A summarising server asks the host's model to condense a document rather than calling a model itself.
Related terms
More Agents tools MCP terms
- MCP server
- MCP tool
- MCP transport
- Memory consolidation
- Memory retrieval
- Model Context Protocol
- Model routing
- Multi-agent system
Where you learn it
MCP sampling is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.