TeamCityCAUTION
Model Context Protocol (MCP) server for JetBrains TeamCity: control builds, tests, agents and configs from AI coding assistants.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/Daghis/teamcity-mcp/actions/workflows/ci.yml) [](https://github.com/Daghis/teamcity-mcp/actions/workflows/codeql.yml) [](https://codecov.io/gh/Daghis/teamcity-mcp) [](LICENSE)
A Model Control Protocol (MCP) server that bridges AI coding assistants with JetBrains TeamCity CI/CD server, exposing TeamCity operations as MCP tools.
[!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 [Cec66c2be5fb7OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add teamcity-mcp --env TEAMCITY_TOKEN=${TEAMCITY_TOKEN} -- npx -y @daghis/[email protected]Exposed tools (12)
12 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Updated | read | New description |
bare | read | no outputSchema |
failing-tool | read | A tool that fails |
list_projects | read | list projects |
new | read | desc |
ping | read | Test connectivity |
strict_list | read | declares strict list outputSchema |
tool1 | read | First tool |
tool2 | read | Second tool |
tool3 | read | Third tool |
validated-tool | read | A tool with validation |
with_schema | read | declares an outputSchema |
Trust audit
CAUTIONgrade B · trust 83/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (19)
'-----BEGIN RSA PRIVATE KEY-----\nfake\n-----END RSA PRIVATE KEY-----',
async () => '-----BEGIN RSA PRIVATE KEY-----\nfake\n-----END RSA PRIVATE KEY-----'
.prettierignore
.release-please-config.json
.release-please-manifest.json
.openapi-generator-ignore
'teamcity.ssh.agent.key': 'id_rsa',
property: [{ name: 'teamcity.ssh.agent.key', value: 'id_rsa' }],'teamcity.ssh.agent.key': 'id_rsa',
{ name: 'teamcity.ssh.agent.key', value: 'id_rsa' },{ name: 'teamcity.ssh.agent.key', value: 'id_rsa' },join(__dirname, '../../package.json'), // source: src/utils/ -> package.json
import type { ActionResult, BuildRef, TriggerBuildResult } from '../../types/tool-results';import packageJson from '../../package.json';
const tsxPath = join(__dirname, '../../node_modules/tsx/dist/cli.mjs');
const serverPath = join(__dirname, '../../src/index.ts');
baseUrl = `http://127.0.0.1:${address.port}`;@modelcontextprotocol/sdk, axios, axios-retry, tslib, winston, zod, @esbuild-plugins/tsconfig-paths, @eslint/js
axios, typescript
Gates applied: no_behavioural_pass.
ec66c2be5fb7full audit observations/trust-audit/mcp-server/daghis__teamcity-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | ec66c2be5fb7 | CAUTION | B | 83 | first audit |
Questions
What is the TeamCity MCP server?
Model Context Protocol (MCP) server for JetBrains TeamCity: control builds, tests, agents and configs from AI coding assistants.
What tools does TeamCity expose?
12 in total: 12 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is TeamCity safe to connect to an agent?
With care. The audit graded it B (83/100) and found 19 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does TeamCity need?
It reads CODECOV_TOKEN, TEAMCITY_API_TOKEN and TEAMCITY_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does TeamCity run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @teamcity/client at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (ec66c2be5fb7), read on 2026-10-08. The repository is watched and re-audited when it changes.