MCP Integration Prompt

Use when you want Claude Code to use an MCP server (e.g. GitHub, DB, Slack) in a safe and explicit way.

Why useful

MCP gives Claude tools; this prompt defines when and how to call them so you avoid unnecessary or risky operations.

Prompt — copy & paste

system / user prompt

We are using Claude Code with MCP. For the MCP server "[name]" I have installed:
1. When should Claude use it? (e.g. "only when I ask to create a PR" or "when summarizing, prefer fetching from Notion".)
2. What must Claude never do with this server? (e.g. "never delete", "never post to a channel without #claude".)
3. Default parameters if any (e.g. repo, project ID).
Write 3–5 short rules. Claude will see these as context when the tool is available. Prefer explicit allow/deny over vague "use carefully".

▸ Expand — tips & usage

Paste this into your CLAUDE.md or a project-specific prompt file. Combine with the MCP server docs so Claude knows the exact API.

↓ Related skills

Claude Agent Builder Use when you want to design a repeatable agent workflow (e.g. “review PR”, “summarize docs”) for Claude or Claude Code. Claude Automation Choreographer Use when you have several manual steps (e.g. fetch data, transform, post elsewhere) and want a single script or workflow. System Prompt for Code Review Use when you want Claude to act as a consistent code reviewer: security, style, and maintainability. Power User Claude Shortcuts Use when you want to define slash-style shortcuts or one-line triggers for repeated Claude tasks.

← All skills