MCP Server

Zuul CI — build failure analysis, log search, pipeline status, and job configuration

Local serverstdioPython

What is the MCP MCP server?

Zuul CI — build failure analysis, log search, pipeline status, and job configuration. That is what the mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

47 tools, 3 prompts, 3 resources — covering builds, logs, pipelines, jobs, infrastructure, and live status. Works with Claude Code, Claude Desktop, Cursor, Codex, Windsurf, and any MCP-compatible client.

The tools it exposes

The server publishes 3 tools. What each one is for:

  • Buildsets — The Buildsets tool exposed by this server
  • Infrastructure — The Infrastructure tool exposed by this server
  • Architecture — The Architecture tool exposed by this server

Getting it running

Installation goes through your MCP client rather than a global install: point it at mcp-zuul on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What it needs from you

Configuration is passed through the environment: ZUUL_URL, ZUUL_DEFAULT_TENANT, ZUUL_USE_KERBEROS, ZUUL_VERIFY_SSL, ZUUL_AUTH_TOKEN, LOGJUICER_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP's toolset — Buildsets, Infrastructure, Architecture — is a fair guide to whether it matches your workflow. It is maintained by imatza-rh; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
BuildsetsThe Buildsets tool exposed by this server.
InfrastructureThe Infrastructure tool exposed by this server.
ArchitectureThe Architecture tool exposed by this server.

How to install the MCP MCP server

{
  "mcpServers": {
    "zuul": {
      "command": "uvx",
      "args": ["mcp-zuul"],
      "env": {
        "ZUUL_URL": "https://softwarefactory-project.io/zuul",
        "ZUUL_DEFAULT_TENANT": "rdoproject.org"
      }
    }
  }
}

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

Configuration

VariableDescriptionRequired
ZUUL_URLEndpoint or connection string the server talks to.Yes
ZUUL_DEFAULT_TENANTConfiguration value read at startup.Optional
ZUUL_USE_KERBEROSConfiguration value read at startup.Optional
ZUUL_VERIFY_SSLConfiguration value read at startup.Optional
ZUUL_AUTH_TOKENCredential the server authenticates with.Yes
LOGJUICER_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use MCP to Buildsets.
  • Use MCP to Infrastructure.
  • Use MCP to Architecture.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (Buildsets, Infrastructure, Architecture) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.