AgentProtocol.ai
//reference

AI agent protocol glossary

The vocabulary of AI agent protocols, defined in plain language. Terms are grouped by category; many link to a fuller guide.

Concepts

AI agentConcepts

A software system that uses a model (often an LLM) to pursue goals with some autonomy — planning, calling tools, and acting over multiple steps rather than answering a single prompt.

See alsoTool use,Orchestration
Agent protocolConcepts

A shared set of rules for how agents exchange messages, tasks, tools or context. Also the name of a specific community REST specification (Agent Protocol).

See alsoMCP,A2A
Tool useConcepts

The pattern of an agent invoking external functions, APIs or data sources during a task. MCP standardises how those tools are described and called.

See alsoMCP,Function calling
InteroperabilityConcepts

The ability for agents, tools and platforms from different vendors to work together through shared protocols instead of one-off custom integrations.

See alsoA2A,MCP
Capability discoveryConcepts

How one system learns what another can do at runtime — for example, listing MCP tools or reading an A2A agent card before delegating a task.

See alsoAgent card,MCP
OrchestrationConcepts

Coordinating multiple steps, tools or agents toward a goal — deciding what runs, in what order, and how results flow between components.

See alsoAI agent,A2A
AI agent APIConcepts

An HTTP interface that lets clients start, monitor and retrieve results from an agent — either a bespoke API or one following a spec like Agent Protocol.

See alsoREST,Agent Protocol

Protocols

A2A

Agent cardA2A

A machine-readable document (in A2A) describing an agent's identity, capabilities and endpoints, so other agents can discover and call it.

See alsoA2A,Capability discovery

Foundations

JSON-RPCFoundations

A lightweight remote-procedure-call protocol encoded in JSON. Both MCP and A2A build on JSON-RPC-style request/response messages.

See alsoMCP,A2A
RESTFoundations

An architectural style for HTTP APIs based on resources and standard methods (GET, POST…). The Agent Protocol spec and many AI agent APIs are RESTful.

See alsoAgent Protocol,AI agent API
Function callingFoundations

A model capability where the LLM emits a structured call to a named function with arguments. It underpins tool use and maps naturally onto MCP tools.

See alsoTool use,MCP