Happy slice of mcp pizzaMCP.pizza

teamcity-mcp

MCP.Pizza Chef: Daghis

teamcity-mcp lets you control your JetBrains TeamCity continuous integration server directly from AI coding assistants like Claude Code, Cursor, or Windsurf. You can start builds, monitor progress, fetch logs, and manage build configurations and agents without leaving your development environment. It requires a TeamCity server (2020.1 or newer) with an API token and Node.js 20+. Setup involves adding the MCP server to your AI app with your TeamCity credentials. It supports safe Dev mode and full management mode for advanced control.

Coding
Other

Use This MCP server To

Trigger a TeamCity build from my coding assistant Check the status of running or past builds Fetch build logs and test failure details List projects and build configurations Create or clone build configurations Manage build agents and queue Adjust build parameters and triggers

README

TeamCity MCP Server

CI CodeQL codecov License: MIT

A Model Control Protocol (MCP) server that bridges AI coding assistants with JetBrains TeamCity CI/CD server, exposing TeamCity operations as MCP tools.

TeamCity Server MCP server

Note

Project status (June 2026): stable, low-key maintenance. This does what it set out to do and is no longer under active development. It still works and stays installable; issues and PRs may get slow or no response, and security fixes are best-effort.

JetBrains now ships official AI integration for TeamCity — a built-in MCP and the TeamCity CLI with an installable agent skill — which is the better default for most workflows. See How this compares to JetBrains' official tooling below before adopting.

Overview

The TeamCity MCP Server allows developers using AI-powered coding assistants (Claude Code, Cursor, Windsurf) to interact with TeamCity directly from their development environment via MCP tools.

Upgrading from 1.x? Version 2.0.0 moved 15 tools from Dev to Full mode, including queue management, agent compatibility checks, and server health monitoring. If you relied on these tools in Dev mode, switch to MCP_MODE=full or use runtime mode switching (v2.1.0+). See CHANGELOG.md for details.

Features

🚀 Two Operational Modes

teamcity-mcp FAQ

Can I use this to trigger and monitor TeamCity builds from my AI assistant?
Yes — teamcity-mcp lets you start builds, check their status, and fetch logs directly from AI coding assistants like Claude Code or Cursor.
Can I manage build configurations and agents with this?
Yes — in Full mode, you can create, clone, and edit build configurations, manage agents, and adjust parameters.
Which AI apps support teamcity-mcp?
It works with Cursor and Windsurf, and also Claude Code supports it.
Do I need a TeamCity account or token?
Yes — you must have a TeamCity Server (2020.1 or newer) with REST API access and an authentication token.
How hard is it to set up?
Setup is copy-paste-config level — you configure environment variables or CLI options with your TeamCity URL and token, then add it to your AI app's MCP servers.
Does it require installing software?
You run it via npx (Node.js 20+ required) or from source; no complex build needed.
Is this the official JetBrains AI integration?
No — JetBrains now offers built-in AI MCP support and a CLI tool, which are recommended for most users.
Can I switch between safe and full control modes?
Yes — you can toggle between Dev mode (safe operations) and Full mode (full management) at runtime without restarting.