MCP server · Developer tools
Reado MCP server
Lets your coding AI read your review comments and tasks in Reado, then mark each one done or failed.
Reado is a code reading app. It is made for reviewing code rather than writing it. This MCP server is the part that lets your AI assistant see the comments and tasks you left while reading, so it can work through them for you.
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 an app. Here, that app is Reado, the code reading tool where you leave review comments. Once this helper is connected, your AI can look up your open tasks and comments in Reado, and mark them done or failed as it works.
What this MCP server does
You read code in Reado and leave comments. Comments marked as tasks become a work list. When you click Send review, Reado hands that list to the AI running in its terminal. The AI reads your tasks and comments through this helper, makes the changes in your code, then marks each task done or failed. Reado shows you the result live, and resolved comments move to history.
What you can do with it
- See the list of open review tasks in your project
- Read the comments you left, anchored to exact lines
- Mark a task as done once the fix is made
- Mark a task as failed with a short reason
- Check what you have already read and what changed since
- Look at your bookmarks in the project
- Inspect the app preview in the browser, including the page, console and network
Try asking your AI
- “Show me my open review tasks in this project and start with the riskiest one”
- “Read the comment on line 42 of auth.js and fix it”
- “Mark task 7 as done”
- “Mark task 9 as failed because the test setup is missing”
- “What have I not read yet in this branch”
What it gives back to you
It gives your AI the list of tasks and comments, with the file and line each one points at. It also returns your reading progress and bookmarks, so the AI knows what you have already looked at. When the AI marks a task done or failed, that change shows up in Reado right away. In the chat, you mostly see short answers and confirmations, while the real work appears in the Reado window.
Before you start
What you need
- The Reado app installed on your computer
- The reado command-line tool installed, which the app sets up from Settings, Command-line tool
- A coding agent launched inside Reado, such as Claude, Codex or Copilot
Good to know
The AI can change your code and close your review tasks, so read what it did before you accept it.
Install it with your AI
Add Reado 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 Reado 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 4,609 MCP servers here for you.
Who it's for
Developers and reviewers who read a lot of AI-written code and want their assistant to work through their review comments.
