Glossary — Agentic AI

What is an MCP Prompt?

1 min read Updated

An MCP prompt is a reusable, parameterized prompt template exposed by an MCP server that provides standardized workflows and interaction patterns for AI agents — like templates for common tasks.

WHY IT MATTERS

MCP prompts are the third capability type alongside tools and resources. While tools enable actions and resources provide data, prompts provide templates for common agent interactions — standardizing how agents approach recurring tasks.

A prompt might define a workflow like 'analyze this DeFi position' with parameters for the protocol, position ID, and risk tolerance. The agent fills in the parameters and gets a well-structured prompt optimized for that specific task.

Prompts are particularly useful for complex workflows that require specific sequencing or domain knowledge. Rather than hoping the agent figures out the right approach, prompts encode best practices into reusable templates.

FREQUENTLY ASKED QUESTIONS

How are MCP prompts different from system prompts?
System prompts configure the agent's overall behavior. MCP prompts are task-specific templates served dynamically by MCP servers. Think of system prompts as the agent's personality and MCP prompts as standardized workflows it can invoke.
When should I use MCP prompts vs tools?
Use tools when the agent needs to take an action (send transaction, query API). Use prompts when you want to guide the agent through a specific reasoning workflow or standardize how it approaches a type of task.
Are MCP prompts widely used?
Prompts are the least-adopted MCP capability so far. Tools dominate current usage. Prompts are most valuable in enterprise settings where standardizing agent behavior across teams matters.

FURTHER READING

BUILD WITH POLICYLAYER

Non-custodial spending controls for AI agents. Setup in 5 minutes.

Get Started