MCP tools for AI coding agents
Choose MCP tools for AI coding agents without giving them unnecessary access, noisy context or unsafe write capabilities.
Quick answer
Give an AI coding agent the smallest MCP toolset needed for the task: repo, docs, browser or issue tracker. Add write access only when the workflow truly needs it.
Tool categories
Separate read tools, write tools, browser tools, documentation tools and project management tools. Each category needs a clear reason to be present.
Risk check
Too many tools make agent behavior harder to predict. The goal is leverage, not a giant permission surface.
FAQ
Should every agent have every MCP tool?
No. Start narrow and add tools only when a task proves the missing capability.
Design an MCP toolset
Related guides
Claude Code MCP: Connect Servers & Tools
Claude Code MCP (Model Context Protocol) lets you plug external tools and data into Claude. Full guide: how to add an MCP server, list available ones, and the patterns that work.
A Claude Code conversation can only do so much with the tools shipped in the box. The moment you want Claude to touch Notion, Stripe, your AWS account, a specific database you need MCP. MCP (Model Context Protocol) is the standard that connects Claude to external tools. Here's what it is, how to add servers, and the patterns that don't waste your time. What MCP actually is MCP is an open protocol. A small server process (the "MCP server") exposes a set of tools. Claude Code (the "MCP client") talks to it over stdio or HTTP. When Claude needs to call one of those tools, it sends a JSON RPC request; the server runs the function and returns the result. Three pieces: MCP server the process that exposes tools. Usually npx installable. Examples: filesystem, GitHub, Notion, Stripe, Postgres. MCP client Claude Code itself. It manages connections, surfaces tools to the…
Read the guideConnect Claude to Notion, Gmail & Drive
Claude Code MCP servers let Claude read and write Notion, Gmail, and Google Drive. Step-by-step setup guide for the three most useful ones.
Claude out of the box knows text. Claude connected to your tools knows your business. The bridge is MCP Model Context Protocol. It's an open standard that lets Claude talk to external services through a local server. Once connected, Claude can read your Notion pages, search your emails, and list your Drive files as naturally as it reads your code. Here's how to set it up for the three tools I use most. What MCP actually is An MCP server is a small process running locally that exposes tools Claude can call. When you ask Claude "what did I write in my Notion project notes?", Claude calls the Notion MCP tool, gets the content, and responds with it. Everything goes through your machine. Your data doesn't leave to a third party service it goes from your tool's API to your local MCP server to Claude. Configuration lives in /.claude/settings.json under…
Read the guideBuilding AI agents that actually work
Most 'agents' are brittle pipelines dressed up with AI. Here's the anatomy of a reliable agent, three patterns that hold up in production, and when to use n8n vs code.
Everyone is building agents. Most of them break on the third run. The failure mode is always the same: the AI is asked to do too much, in the wrong place. The agent fails not because AI is unreliable it's because the architecture made reliability impossible. Here's what I've learned building agents that actually run week after week. The anatomy of a reliable agent Every agent that works has three parts, and only one of them should involve AI. Trigger something deterministic starts the agent. A schedule, a webhook, a file drop, a form submission. Not "whenever the AI decides it's time." Context the agent gathers what it needs before calling the AI. The document, the data, the user preferences, the constraints. The AI call happens with full context, not halfway through discovery. Action after the AI produces output, something deterministic happens with it. It gets saved, sent, logged, or…
Read the guide