Glossary category

Tools and protocols

The interfaces and contracts that let AI systems act on software and external services.

What belongs here

Tool calling, capabilities, gateways, protocols, schemas, and interoperability boundaries.

What belongs elsewhere

The reasoning policy that chooses a tool and the security policy that authorizes it.

Adjacent categories

Definitions in this category

stable

Agent Card

An A2A document that declares an agent's identity, interfaces, capabilities, skills, and security requirements for discovery.

Agent2Agent Protocol (A2A)

An open protocol for discovery, messaging, and asynchronous task collaboration between independent and potentially opaque agent systems.

Application programming interface (API)

A defined contract through which software components request capabilities or exchange data.

Latency

Elapsed time from a request or event to its response or completion.

MCP capability negotiation

The initialization exchange in which an MCP client and server declare the optional protocol features each supports.

MCP client

The protocol component maintained by an MCP host that establishes and manages a connection to one MCP server.

MCP host

The AI application that manages model interaction, user experience, policy, and connections to one or more MCP clients and servers.

MCP prompt

A reusable, user-selectable template exposed by an MCP server to structure messages or workflows for a model interaction.

MCP resource

Contextual data exposed by an MCP server under a URI so a client or application can retrieve and supply it to a model.

MCP server

A program or service that exposes MCP capabilities such as tools, resources, and prompts to connected clients.

MCP tool

A model-discoverable executable function exposed by an MCP server with a name, description, and input schema.

Model Context Protocol (MCP)

An open client-server protocol for connecting AI applications to tools, resources, and reusable prompts through standardized discovery and invocation.

Rate limit

A provider or system constraint on requests, tokens, compute, or actions permitted within a time window.

Sandbox

An isolated execution environment that limits access to files, processes, networks, credentials, or other host resources.

Throughput

The amount of work a system completes per unit time.

Tool

An executable capability exposed to an AI application or agent, such as reading a file, querying an API, running code, or changing external state.