The TeamCity MCP Server is a Model Control Protocol server that connects AI coding assistants with JetBrains TeamCity CI/CD server, allowing direct interaction with TeamCity operations through MCP tools.
From the registry: MCP server exposing JetBrains TeamCity CI/CD workflows to AI coding assistants
Please install the `teamcity` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **TeamCity Server 2020.1+** — With REST API access and authentication token
- **Node.js 20.10.0+** — Required for npx (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@daghis/teamcity-mcp"]
- required environment variables:
- `TEAMCITY_URL`: TeamCity server URL (example: `https://teamcity.example.com`)
- `TEAMCITY_TOKEN`: TeamCity authentication token (example: `<tc_your_token>`)
- optional environment variables:
- `MCP_MODE`: dev (31 tools) or full (87 tools) (example: `dev`)
Note: TeamCity CI/CD MCP with 2 modes: dev (31 tools, safe) and full (87 tools, includes destructive ops). Runtime mode switching available in v2.1.0+.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.TEAMCITY_TOKENrequiredToken for authenticating with TeamCity.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.