Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / model-context-protocol-mcp

Model Context Protocol (MCP)

An open protocol published by Anthropic in November 2024 for interoperability between models and tools — standardising how servers expose tools, resources, and prompts to AI clients.

What this means in practice

MCP is becoming the reference A2A-style interoperability layer; governance concerns include auth, audit, and tool-source provenance.

Synonyms

MCP , Anthropic Model Context Protocol

Related Terms Network

This diagram shows how Model Context Protocol (MCP) connects to other concepts in the COMPEL body of knowledge. Each linked node is a term you can explore in turn.

Related terms for Model Context Protocol (MCP) Network graph showing 4 related glossary terms connected to Model Context Protocol (MCP). Model Context … Tool regis… Tool schem… Agent-to-a… Tool use /…
4 related concepts connected to Model Context Protocol (MCP).

The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.

Accessible list of related terms
  • Tool registry — An authoritative inventory of tools — with schemas, permissions, owners, deprecation state, and audit log — that an agent may call.
  • Tool schema — The JSON-schema (or equivalent structured) definition of a tool's parameters, types, and constraints.
  • Agent-to-agent (A2A) protocol — The communication mechanism between AI agents — specifying message format, authentication, authorization scope, rate limiting, and audit logging.
  • Tool use / function calling — A prompt pattern authorizing the model to request named functions with structured arguments — searching the web, reading a database, calling a calculator, triggering an API — rather than generating all answers from its weights.

See also

  • Tool registry — An authoritative inventory of tools — with schemas, permissions, owners, deprecation state, and audit log — that an agent may call.
  • Tool schema — The JSON-schema (or equivalent structured) definition of a tool's parameters, types, and constraints.
  • Agent-to-agent (A2A) protocol — The communication mechanism between AI agents — specifying message format, authentication, authorization scope, rate limiting, and audit logging.
  • Tool use / function calling — A prompt pattern authorizing the model to request named functions with structured arguments — searching the web, reading a database, calling a calculator, triggering an API — rather than generating all answers from its weights.