Skip to content
MCP server

TeamCity CI/CD

Read-only view of TeamCity builds, logs, failed tests, queue and agents

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, macOS, Linux
Runs
Locally
Version
1.0.1
Listing updated
3 days ago

About TeamCity CI/CD

TeamCity CI/CD is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Debugging a failed CI run usually means hopping between build pages. This server's diagnose_build tool answers why a build failed in one call, returning problems, failed tests (unmuted first) and the error lines of the log. Other tools search build history by config, branch, status or date, page through logs with tail and line-range support, and run full-text search inside a log.

It offers 29 tools covering projects, build configurations, builds, test results, problems, the queue, agents and VCS changes. A fuzzy find_build_config tool flags ambiguous matches, and get_build_chain shows snapshot dependencies upstream and downstream.

The server only issues GET requests, and every tool is annotated readOnlyHint. The README advises creating a token scoped per project with the Read-only preset so the token itself cannot change anything. It runs with uvx on Python 3.11 or newer.

Install

Run in a terminal

claude mcp add teamcity --env TEAMCITY_BASE_URL='<TEAMCITY_BASE_URL>' --env TEAMCITY_TOKEN='<TEAMCITY_TOKEN>' -- uvx readonly-mcp-teamcity

Add to claude_desktop_config.json

{
  "mcpServers": {
    "teamcity": {
      "command": "uvx",
      "args": [
        "readonly-mcp-teamcity"
      ],
      "env": {
        "TEAMCITY_BASE_URL": "<TEAMCITY_BASE_URL>",
        "TEAMCITY_TOKEN": "<TEAMCITY_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "teamcity": {
      "command": "uvx",
      "args": [
        "readonly-mcp-teamcity"
      ],
      "env": {
        "TEAMCITY_BASE_URL": "<TEAMCITY_BASE_URL>",
        "TEAMCITY_TOKEN": "<TEAMCITY_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "teamcity": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "readonly-mcp-teamcity"
      ],
      "env": {
        "TEAMCITY_BASE_URL": "<TEAMCITY_BASE_URL>",
        "TEAMCITY_TOKEN": "<TEAMCITY_TOKEN>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "teamcity": {
      "command": "uvx",
      "args": [
        "readonly-mcp-teamcity"
      ],
      "env": {
        "TEAMCITY_BASE_URL": "<TEAMCITY_BASE_URL>",
        "TEAMCITY_TOKEN": "<TEAMCITY_TOKEN>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "teamcity": {
      "command": "uvx",
      "args": [
        "readonly-mcp-teamcity"
      ],
      "env": {
        "TEAMCITY_BASE_URL": "<TEAMCITY_BASE_URL>",
        "TEAMCITY_TOKEN": "<TEAMCITY_TOKEN>"
      }
    }
  }
}

Configuration

  • TEAMCITY_BASE_URLTeamCity server base URL (e.g., https://teamcity.example.com)Required
  • TEAMCITY_TOKENTeamCity REST API bearer token (scope it read-only)Required

Tools this server provides (15)

Taken from the project documentation; the running server may differ.

search_projects
Searches projects and browses the hierarchy.
get_project_details
Returns a project's children, configs and parameters.
search_build_configs
Searches build configurations.
find_build_config
Fuzzy searches build configs.
get_build_config_details
Returns steps, triggers, parameters and VCS roots.
get_build_config_branches
Lists branches a config can build.
search_builds
Searches build history.
get_build_details
Returns one build's details.
get_build_statistics
Returns durations, test counts and coverage.
get_build_chain
Shows the snapshot-dependency chain.
get_build_log
Pages through a build log.
search_build_log
Full-text searches a build log.
diagnose_build
Explains why a build failed.
get_build_test_results
Lists test occurrences for a build.
get_test_details
Returns one test's failure and history.

What it does

One-call diagnosis
diagnose_build gathers problems, failed tests and log errors.
Log search
Paginate logs or search them with context.
Build history
Filter builds by config, project, status, branch or date.
Config discovery
Fuzzy find build configurations and read their steps and triggers.
Dependency chains
See upstream and downstream snapshot dependencies.
Read-only by design
Only GET requests; scoped read-only tokens recommended.

Good for

  • Find out why last night's build failed
  • Search a log for an error message
  • List which tests are failing and whether they are muted
  • Look up which branches a configuration can build

Pricing

Open source

Public repository, run locally; needs a TeamCity server

Prices change. Check blog.wentland.io before you buy.

TeamCity CI/CD FAQ

Can it trigger or cancel builds?

No. It only issues GET requests and cannot trigger, cancel, pin, tag or modify anything.

How do I authenticate?

Set TEAMCITY_BASE_URL and TEAMCITY_TOKEN; use a token limited per project with the Read-only preset.

How many tools?

29, all reads.

How do I run it?

With uvx, on Python 3.11 or newer.

Is TeamCity CI/CD free?

Yes. TeamCity CI/CD is open source, so you can use and self-host it for free.

How do I add TeamCity CI/CD to Claude Code?

Run this command in your terminal: claude mcp add teamcity --env TEAMCITY_BASE_URL='<TEAMCITY_BASE_URL>' --env TEAMCITY_TOKEN='<TEAMCITY_TOKEN>' -- uvx readonly-mcp-teamcity

What are the best alternatives to TeamCity CI/CD?

The closest alternatives to TeamCity CI/CD are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to TeamCity CI/CD

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools