Complete AI Training

MCP server · Productivity

Backlog MCP server

by corbym

Lets your AI read and update your project backlog, stored as simple markdown files in your repo.

Flow diagram: you ask your AI “Which stories are still in progress?”, on your own computer the Backlog MCP server works with your backlog files, and you get back answers and updated files.

This is a small helper program that connects your AI assistant to a project backlog kept as plain text files inside your code folder. Instead of juggling a separate planning tool, your stories, epics and notes live right next to your code and your AI can read and update them for you. It is handy if you already work with an AI coding assistant and want it to help keep your task list tidy.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to something else. This one connects your AI to a backlog stored as markdown files in your project, so the AI can look up stories, change their status, or add notes when you ask. You run it on your own computer, and it just reads and writes those files.

What this MCP server does

You ask your AI something like "what stories are still in progress?" The AI passes that request to this helper program. The helper reads the markdown files in your requirements folder and finds the matching stories. It sends the list back, and the AI shows it to you in the chat. If you ask it to change something, like marking a story done, the helper updates the files for you.

Flow diagram: you ask your AI “Which stories are still in progress?”, on your own computer the Backlog MCP server works with your backlog files, and you get back answers and updated files. Click to zoom

What you can do with it

  • List stories, filtered by epic, status or type
  • Read the full content of a single story
  • Create new epics and stories with the next available ID
  • Update a story's status, like draft, in-progress or blocked
  • Tick off acceptance criteria on a story
  • Append a timestamped note to a story
  • Get a high-level summary of epics and story counts

Try asking your AI

  • “List all stories that are still in progress”
  • “Show me the full content of STORY-042”
  • “Add a note to STORY-007 saying the login bug is fixed”
  • “Create a new story under EPIC-001 called Password reset”

What it gives back to you

You get back plain answers in the chat: lists of stories, the full text of a story file, counts by status, or a short confirmation that a change was made. If the AI creates or updates something, it tells you what it did. The actual files in your requirements folder are changed on disk, so you can open them yourself or commit them with git.

Before you start

What you need

  • The backlog-mcp program installed on your computer (Homebrew, a release binary, or Go)
  • A requirements folder in your project (run the init command once to create it)
  • An MCP client like Claude Code or VS Code with GitHub Copilot agent mode

Good to know

It can change and delete content in your backlog files, so keep your work in git and review changes before committing.

Install it with your AI

Add Backlog MCP server 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 Backlog MCP server, 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 product people who keep their backlog as markdown files and want their AI assistant to help manage it.