Complete AI Training

MCP server · Developer tools

TeamCity MCP server

by Daghis

Lets your AI check builds, read logs, and trigger or manage TeamCity builds for you.

Flow diagram: you ask your AI “Why did last night's tests fail?”, the TeamCity MCP server connects it to TeamCity, and you get back answers in plain language.

This is a small helper that connects your AI assistant to JetBrains TeamCity, the tool many teams use to build and test their software automatically. Once it is set up, you can ask your AI things like why a build failed or start a new build, and it will go and do that for you. It is handy for developers and anyone who spends time checking build results.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app, and here that app is TeamCity. With this helper running, your AI can look things up in TeamCity or make changes there when you ask. You do not need to understand how it works inside; you just tell your AI what you want.

What this MCP server does

You ask your AI a question about your TeamCity builds, like why last night's tests failed. Your AI passes that request to this helper program. The helper then talks to your TeamCity server using a token you provide, fetches the information or performs the action, and sends the result back. Your AI shows you the answer in plain language, such as a list of failing tests or a confirmation that a build was started.

Flow diagram: you ask your AI “Why did last night's tests fail?”, the TeamCity MCP server connects it to TeamCity, and you get back answers in plain language. Click to zoom

What you can do with it

  • Trigger a new build on a branch
  • Check the status of a running or finished build
  • Fetch and read build logs
  • List failing tests and see details about them
  • List projects, build configurations, and the build queue
  • Create or clone build configurations (in full mode)
  • Manage build steps, triggers, and parameters (in full mode)

Try asking your AI

  • “Build the frontend on the feature branch”
  • “Why did last night's tests fail?”
  • “Show me the last 10 builds for the mobile app”
  • “Create a new build config for the payments service”

What it gives back to you

You get answers in the chat, like a list of builds, a summary of test failures, or the text of a build log. If you asked it to start a build or change something, it tells you what it did. Some results come back as structured data, but your AI turns that into normal sentences for you.

Before you start

What you need

  • Node.js version 20.10.0 or newer installed on your computer
  • A TeamCity server (version 2020.1 or later) with API access turned on
  • A TeamCity authentication token (a kind of password for apps, created in your TeamCity account settings)

Good to know

Full mode can make big changes like deleting projects or managing agents, and those actions are hard to undo, so stick with dev mode unless you really need the extra tools.

Install it with your AI

Add TeamCity 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 TeamCity 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, testers, and DevOps engineers who use TeamCity and want to check or manage builds without leaving their AI assistant.