Teamcity MCP Server

A comprehensive Model Context Protocol (MCP) server that exposes JetBrains TeamCity as structured AI-ready resources and tools for LLM agents and IDE

Local serverstdioGo

What is the Teamcity MCP MCP server?

If you want an AI assistant working directly with Teamcity MCP, the teamcity mcp mcp server is the bridge. A comprehensive Model Context Protocol (MCP) server that exposes JetBrains TeamCity as structured AI-ready resources and tools for LLM agents and IDE plugins.

What Teamcity MCP does

A comprehensive Model Context Protocol (MCP) server that exposes JetBrains TeamCity as structured AI-ready resources and tools for LLM agents and IDE plugins.

Key capabilities

  • MCP Protocol Compliance — Full JSON-RPC 2.0 over HTTP/WebSocket support
  • TeamCity Integration — Complete REST API integration with authentication
  • Resource Access — Projects, build types, builds, agents, and artifacts
  • Build Operations — Trigger, cancel, pin builds, set tags, download artifacts, search builds
  • Advanced Search — Comprehensive build search with multiple filters (status, branch, user, dates, tags)
  • Production Ready — Docker, Kubernetes, monitoring, caching, and comprehensive logging
  • Environment-Based Configuration — No config files needed, everything via environment variables
  • AI Time Awareness — Provides real current date/time to prevent AI models from using training data dates

Installing the teamcity mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

Before the server will start you need to supply 8 environment variables: TC_URL, TC_TOKEN, SERVER_SECRET, LOG_LEVEL, LOG_FORMAT, TLS_CERT, TLS_KEY, CACHE_TTL. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Cloud and DevOps servers put infrastructure on speaking terms with your assistant, so "why is this broken?" is answered from real state rather than a generic checklist. Teamcity MCP sits in that group. Worth comparing against the other cloud devops servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by itcaat, written in Go.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the teamcity mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

How to install the Teamcity MCP MCP server

{
  "mcpServers": {
      "teamcity": {
        "command": "docker",
        "args": [
          "run",
          "--rm",
          "-i",
          "-e",
          "TC_URL",
          "-e",
          "TC_TOKEN",
          "itcaat/teamcity-mcp:latest",
          "--transport",
          "stdio"
        ],
        "env": {
          "TC_URL": "https://your-teamcity-server.com",
          "TC_TOKEN": "your-teamcity-api-token"
        }
      }
    }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
TC_URLEndpoint or connection string the server talks to.Yes
TC_TOKENCredential the server authenticates with.Yes
SERVER_SECRETCredential the server authenticates with.Yes
LOG_LEVELConfiguration value read at startup.Optional
LOG_FORMATConfiguration value read at startup.Optional
TLS_CERTConfiguration value read at startup.Optional
TLS_KEYCredential the server authenticates with.Yes
CACHE_TTLConfiguration value read at startup.Optional

Frequently asked questions

It connects Teamcity MCP to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Teamcity MCP directly.