← Back to glossaryGlossary

Agent Capability

Reviewed 19 July 2026Canonical definitionPart of: MCP & Agent Protocol Terms →

An agent capability is a specific skill or function an agent can perform, such as searching a database, calling an API, writing code, or sending a message. Capabilities are usually scoped one by one rather than granted to an agent wholesale, so each can be reasoned about on its own.

§01 / QUESTIONSterm: Agent Capability
Questions

Common questions.

What is Agent Capability?

An agent capability is a specific skill or function an agent can perform, such as searching a database, calling an API, writing code, or sending a message.

How does Agent Capability work?

Capabilities are usually scoped one by one rather than granted to an agent wholesale, so each can be reasoned about on its own.

Which terms are related to Agent Capability?

Closely related concepts include AI Firewall, Tool Use (Function Calling), A2A Protocol (Agent-to-Agent Protocol), Context Window Poisoning. Each is defined in the Prefactor glossary.

§02 / RELATEDnext: where this fits

See how every agent performs, and make it better

Prefactor helps teams observe, evaluate, and improve their AI agents in production, across every framework and provider.