Complete AI Training

MCP server · Developer tools

Fagan coding pipeline

by motock

Let your AI plan, write, review, and merge small coding tasks in your project.

Flow diagram: you ask your AI “Turn this goal into a plan: add a search box to the settings page”, the Fagan coding pipeline works in steps: plan the work, then write the code, then test and review, and you get back plan, status, and changes.

Fagan is a helper that plugs into your AI coding assistant and runs a small software team for you. One part plans the work, another writes the code, another checks it, and a final step merges it. It is handy if you already use Claude Code and want routine coding tasks handled without doing every keystroke yourself.

What is an MCP server? The 30-second version

On its own, your AI can only chat and suggest things. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. Fagan is that helper, and it connects your AI to a coding pipeline that plans, writes, reviews, and merges changes in your project. When you ask, your AI talks to Fagan, and Fagan does the actual work behind the scenes.

What this MCP server does

You give Fagan a goal, like a small feature or a bug fix, in plain words. Fagan turns that goal into a plan with steps and stories. Then it sends each story to a model that writes the code, runs tests first, and checks the result. A review pass looks at the changes, and a final gate re-runs the tests on the updated branch before anything gets merged. You can watch the whole thing move across a board on a local dashboard.

Flow diagram: you ask your AI “Turn this goal into a plan: add a search box to the settings page”, the Fagan coding pipeline works in steps: plan the work, then write the code, then test and review, and you get back plan, status, and changes. Click to zoom

What you can do with it

  • Turn a plain goal into a plan with steps and stories
  • Send a ready story to a model to write the code
  • Run tests before and after code is written
  • Review the changes and send them back if something looks wrong
  • Merge low-risk changes automatically when they pass
  • Watch progress on a local dashboard
  • Run the pipeline unattended with a scheduler

Try asking your AI

  • “Turn this goal into a plan: add a search box to the settings page”
  • “List the stories that are ready to work on”
  • “Start the next ready story and show me the progress”
  • “Show me what changed in the last merged story”

What it gives back to you

Fagan gives you a plan with stories, a status for each one, and a summary of what was written or changed. You see this in your AI chat as lists, short updates, and links to the changes. The dashboard shows the same information as a board with columns. When something is merged, you get a note about it.

Before you start

What you need

  • A Mac (Linux works with Ollama or LM Studio; Windows is untested)
  • Claude Code installed and logged in
  • GitHub CLI logged in with gh auth login
  • A local model like Ollama or LM Studio if you want to run the writing part for free

Good to know

This pipeline can write code, open pull requests, and merge changes in your project, so start with dry-run and watch a few runs before letting it work on its own.

Install it with your AI

Add Fagan coding pipeline to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Fagan coding pipeline, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Developers and technical teams who use Claude Code and want small coding tasks planned, written, reviewed, and merged with less manual work.