Home Glossary
HomeGlossaryMCP Prompt
MCP Glossary

MCP Prompt

TL;DR

An MCP prompt is a reusable, server-defined message template that clients can surface to users as slash commands or menu items. Prompts let servers ship best-practice workflows (like `/review-pr` or `/debug-error`) that pre-compose context and instructions for the LLM.

In depth

An MCP prompt is a server-authored message template that appears in the host UI for easy reuse. Unlike tools (which the LLM calls autonomously) or resources (which the host reads), prompts are user-triggered: the human picks a prompt, supplies any arguments, and the server returns a composed message that's injected into the conversation.

Prompts are a way for MCP servers to ship workflows, not just primitives. A GitHub MCP could expose a `/review-pr` prompt that takes a PR number, fetches the diff, and produces a pre-composed review prompt for the LLM. Users click once; the server handles all the boilerplate.

Each prompt has a name, description, and optional arguments (with JSON Schema). When invoked, it returns a list of messages that the host adds to the conversation. This gives servers a UI-level presence without building their own UI.

Claude Code surfaces prompts as slash commands; Cursor surfaces them in a palette. Not all hosts support prompts yet, but the feature is part of the MCP spec.

Code example

// Prompt definition
{
  "name": "review-pr",
  "description": "Review a GitHub pull request",
  "arguments": [
    { "name": "pr_number", "description": "PR number", "required": true }
  ]
}

// prompts/get response
{
  "messages": [
    {
      "role": "user",
      "content": {
        "type": "text",
        "text": "Review PR #123 at github.com/acme/app. Focus on: security, performance, style. Here is the diff:\n\n..."
      }
    }
  ]
}

Examples

  • 1
    `/review-pr 123` — GitHub MCP pre-composes a code review request
  • 2
    `/debug-error` — Sentry MCP bundles the most recent error into a debug prompt
  • 3
    `/summarize-week` — Notion MCP compiles your week's pages into a summary prompt
  • 4
    `/explain-query` — Postgres MCP wraps a SQL query for LLM analysis
  • 5
    `/draft-tweet` — Social media MCP produces a tweet-drafting prompt

What it's NOT

  • ✗MCP prompts are NOT system prompts — they're user-triggered message templates.
  • ✗Prompts are NOT automatically applied — the user must invoke them.
  • ✗A prompt is NOT a tool — prompts don't execute; they compose a message.
  • ✗Not all hosts support prompts yet — tool support is universal, prompt support is uneven.

Related terms

MCP ToolMCP ResourcePrompt EngineeringModel Context Protocol (MCP)

See also

  • MCP Prompts

Frequently asked questions

When should I use a prompt vs a tool?

Use a prompt for user-triggered workflows. Use a tool when the LLM should decide autonomously. Prompts are for human-in-the-loop UX.

Can prompts include images?

Yes — prompt messages support text, image, and resource content types.

Which hosts support prompts?

Claude Desktop, Claude Code, and a growing list of third-party hosts. Tool support is universal, prompt support is spreading.

Build with MCP

Browse 300+ MCP servers, explore recipes, or continue learning the MCP vocabulary.

Browse MarketplaceAll terms