TeamCity
Enables AI coding assistants to interact with JetBrains TeamCity CI/CD server through natural language commands. Supports triggering builds, monitoring status, analyzing test failures, and managing build configurations directly from development envir
What is TeamCity?
TeamCity is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai coding assistants to interact with jetbrains teamcity ci/cd server through natural language commands. supports triggering builds, monitoring status, analyzing test failures, and managing bu...
Enables AI coding assistants to interact with JetBrains TeamCity CI/CD server through natural language commands. Supports triggering builds, monitoring status, analyzing test failures, and managing build configurations directly from development envir
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI coding assistants to interact with JetBrains Team
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @daghis/teamcity-mcpManual Installation
npx -y @daghis/teamcity-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use TeamCity
The TeamCity MCP Server bridges AI coding assistants and JetBrains TeamCity CI/CD through natural language commands. It exposes up to 87 tools (31 in default dev mode) for triggering builds, monitoring build status and logs, analyzing test failures, managing build configurations, and handling VCS roots and parameters. It connects to any self-hosted or cloud TeamCity instance via a personal access token and supports multi-server deployments. DevOps engineers and developers use it to interact with their CI/CD pipelines conversationally without switching away from their IDE or AI assistant.
Prerequisites
- Node.js 18+ (for npx execution)
- A running JetBrains TeamCity server (self-hosted or TeamCity Cloud)
- A TeamCity personal access token with appropriate permissions
- The TeamCity server URL (e.g., https://teamcity.example.com)
- An MCP-compatible client such as Claude Desktop or Claude Code
Generate a TeamCity personal access token
In TeamCity, go to your user profile > Access Tokens and create a new token. Grant it the permissions needed for the operations you want to perform (at minimum: View Build Configuration Settings and Run Build).
Add the server to Claude Desktop configuration
Open claude_desktop_config.json and add the teamcity entry with your server URL and token as environment variables. Use dev mode (MCP_MODE=dev) to limit to 31 tools and reduce token overhead; use full for all 87 tools.
{
"mcpServers": {
"teamcity": {
"command": "npx",
"args": ["-y", "@daghis/teamcity-mcp"],
"env": {
"TEAMCITY_URL": "https://teamcity.example.com",
"TEAMCITY_TOKEN": "your_personal_access_token",
"MCP_MODE": "dev"
}
}
}
}Add via Claude Code CLI (alternative)
If using Claude Code in the terminal, use the claude mcp add command to register the server. Pass URL and token as CLI arguments or set environment variables first.
TEAMCITY_URL="https://teamcity.example.com" \
TEAMCITY_TOKEN="your_token" \
claude mcp add teamcity -- npx -y @daghis/teamcity-mcpRestart your MCP client and verify connection
Fully restart Claude Desktop. Ask Claude to list your TeamCity projects or recent builds to verify the connection is working. If using dev mode you have 31 tools available; full mode enables all 87.
Trigger builds and monitor results
Use natural language to trigger builds on specific branches, check for failed tests, or review build logs. The server automatically redacts sensitive values from log output.
TeamCity Examples
Client configuration
claude_desktop_config.json entry for TeamCity MCP in dev mode. Replace the URL and token with your actual TeamCity instance values.
{
"mcpServers": {
"teamcity": {
"command": "npx",
"args": ["-y", "@daghis/teamcity-mcp"],
"env": {
"TEAMCITY_URL": "https://teamcity.example.com",
"TEAMCITY_TOKEN": "your_personal_access_token",
"MCP_MODE": "dev"
}
}
}
}Prompts to try
Natural language prompts for common CI/CD workflows: triggering builds, investigating failures, and managing configurations.
- "Trigger a build for the frontend project on the feature/login branch"
- "Why did last night's nightly build fail? Show me the test failures"
- "List all build configurations in the MobileApp project"
- "Show me the build log for the last failed backend build"
- "What tests have been consistently failing in the last 5 builds?"
- "Create a new build configuration for the API service cloning from the existing backend config"Troubleshooting TeamCity
Authentication errors: 401 Unauthorized
Verify that TEAMCITY_URL does not have a trailing slash and that TEAMCITY_TOKEN matches a valid personal access token (not your password). Tokens are created under your TeamCity user profile > Access Tokens.
Tools for creating or modifying configurations are missing
Configuration management tools are only available in full mode. Set MCP_MODE=full in your env block and restart your MCP client. Note that full mode uses approximately 26,000 tokens for tool definitions.
Build trigger hangs or times out
The default request timeout may be too short for slow TeamCity instances. Add TEAMCITY_TIMEOUT=60000 (milliseconds) to your env block to extend the timeout. Also check that the TeamCity server is reachable from the machine running the MCP server.
Frequently Asked Questions about TeamCity
What is TeamCity?
TeamCity is a Model Context Protocol (MCP) server that enables ai coding assistants to interact with jetbrains teamcity ci/cd server through natural language commands. supports triggering builds, monitoring status, analyzing test failures, and managing build configurations directly from development envir It connects AI assistants to external tools and data sources through a standardized interface.
How do I install TeamCity?
Install via npm with the command: npx -y @daghis/teamcity-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with TeamCity?
TeamCity works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is TeamCity free to use?
Yes, TeamCity is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
TeamCity Alternatives — Similar Cloud Services Servers
Looking for alternatives to TeamCity? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up TeamCity in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use TeamCity?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.