Search builds with filters. Returns compact build summaries.

Args: tenant: Tenant (default from env) project: Project filter pipeline: Pipeline filter job_name: Job name filter change: Change number filter branch: Branch filter patchset: Patchset filter ref: Git ref filter result: Result filter (SUCCESS, FAILURE, TIMED_OUT, SKIPPED, etc.) completed_after: ISO 8601 lower bound on completion time completed_before: ISO 8601 upper bound on completion time started_after: ISO 8601 lower bound on start time started_before: ISO 8601 upper bound on start time limit: Max results, 1-100 (default 20) skip: Pagination offset

Get full build details — log URL, nodeset, artifacts, timing, error detail.

Args: uuid: Build UUID (full or prefix from list_builds) tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant)

Analyze a failed build — which task failed, on which host, with error message.

Parses job-output.json for precise failure data. Prefer diagnose_build for most use cases (adds classification and log context).

Args: uuid: Build UUID tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant)

One-call failure diagnosis — structured failures + relevant log context.

Combines get_build_failures (which task failed, error message) with targeted log grep (surrounding context from job-output.txt). Returns everything needed to understand a failure in a single call.

Use this instead of calling get_build_failures + get_build_log separately.

Args: uuid: Build UUID tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant) brief: Return only classification + root cause (default false). Omits playbooks, log_context, and full task details for ~95% smaller response.

Classify multiple failed builds in one call — returns a triage table.

Runs diagnose_build(brief=True) in parallel for each UUID and returns a compact classification summary. Use instead of calling diagnose_build N times when triaging multiple failures.

Args: uuids: List of build UUIDs to diagnose (max 20) tenant: Tenant (default from env)

One-call diagnosis + test results — combines diagnose_build and get_build_test_results.

Fetches build metadata once, then runs failure analysis and JUnit test parsing in parallel. Saves a round-trip vs calling both tools separately.

Args: uuid: Build UUID tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant) brief: Brief diagnosis (default true). Set false for full failure details.

Search buildsets (groups of builds triggered by a single event).

Args: tenant: Tenant (default from env) project: Project filter pipeline: Pipeline filter change: Change number filter branch: Branch filter ref: Git ref filter result: Result filter completed_after: ISO 8601 lower bound on completion time completed_before: ISO 8601 upper bound on completion time started_after: ISO 8601 lower bound on start time started_before: ISO 8601 upper bound on start time limit: Max results, 1-100 (default 20) skip: Pagination offset include_builds: Fetch full details per buildset (slower, best with limit <= 5)

Get buildset details — result, pipeline, project, change.

Brief (default): compact metadata only. Set brief=False for full details with builds, events, and timing.

Args: uuid: Buildset UUID tenant: Tenant (default from env) url: Zuul buildset URL (alternative to uuid + tenant) brief: Compact response (default true). Set false for full timing/events.

List all jobs in a tenant. Optionally filter by name substring.

Args: tenant: Tenant (default from env) filter: Case-insensitive name substring filter limit: Max results (default 200, 0 for unlimited)

Get job configuration — parent, nodeset, timeout, branches, and all variants.

Args: name: Job name tenant: Tenant (default from env)

Get project configuration — which pipelines and jobs are configured.

Args: name: Project name (e.g. "openstack-k8s-operators/openstack-operator") tenant: Tenant (default from env)

List all pipelines with their trigger types.

Args: tenant: Tenant (default from env)

Get Zuul configuration errors — broken configs, missing refs, syntax errors.

First tool to check when a job isn't being triggered.

Args: tenant: Tenant (default from env) project: Project filter (optional)

List all projects in a tenant. Optionally filter by name substring.

Args: tenant: Tenant (default from env) filter: Case-insensitive name substring filter limit: Max results (default 200, 0 for unlimited)

List nodepool nodes — available, in-use, or provisioning.

Check when jobs are stuck waiting for nodes. Summary by default, set detail=true for individual nodes.

Args: tenant: Tenant (default from env) detail: Include individual node list (default false) limit: Max nodes in detail list (default 200, 0 for unlimited)

List available nodepool labels (node types that jobs can request).

Args: tenant: Tenant (default from env)

List semaphores — resource locks that limit concurrent job execution.

Check when jobs are waiting unexpectedly.

Args: tenant: Tenant (default from env)

List autohold requests — nodes held after failure for debugging.

Args: tenant: Tenant (default from env)

Get details of a specific autohold request.

Args: autohold_id: Autohold request ID (from list_autoholds) tenant: Tenant (default from env)

List system events — config updates, reconfigurations, pipeline changes.

Args: tenant: Tenant (default from env) event_type: Event type filter limit: Max results (default 50) skip: Pagination offset

List nodepool cloud providers with flavors and images.

Args: tenant: Tenant (default from env)

List nodepool disk images with build status and upload artifacts.

Args: tenant: Tenant (default from env)

Get a status badge URL (SVG) for a project's latest buildset result.

Args: project: Project name (e.g. "org/repo") tenant: Tenant (default from env) pipeline: Pipeline filter branch: Branch filter

Get the resolved job graph for a pipeline/project/branch.

Shows which jobs will run with all inheritance resolved, including dependencies. Use to understand job ordering.

Args: pipeline: Pipeline name (e.g. "check", "gate") project: Project name branch: Branch name (default "main") tenant: Tenant (default from env)

List configured source connections — Gerrit, GitHub, GitLab instances.

Shows what code review systems this Zuul instance talks to, with connection type, hostname, and base URL.

Show Zuul system components — schedulers, executors, mergers, web servers.

Get fully-resolved job configuration after inheritance.

Shows final merged nodeset, timeout, and playbooks. Use to understand exactly what a job will do.

Args: pipeline: Pipeline name (e.g. "check", "gate") project: Project name job_name: Job name to resolve branch: Branch name (default "main") tenant: Tenant (default from env) include_vars: Include vars/extra_vars/host_vars/group_vars (default false, can be large)

Get tenant capabilities, auth config, and websocket URL.

Args: tenant: Tenant (default from env)

Read live console output from a RUNNING build via WebSocket.

For RUNNING builds only. For completed builds, use tail_build_log. Requires pip install mcp-zuul[console].

Args: uuid: Build UUID (from get_change_status) tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant) lines: Lines to return from end (default 100, max 500) timeout: Seconds to buffer (default 10, max 30)

Detect anomalous log lines using LogJuicer ML-based analysis.

Requires LOGJUICER_URL to be configured.

Args: uuid: Build UUID tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant)

Read, search, and navigate build log files with grep, line ranges, and error summary.

Args: uuid: Build UUID tenant: Tenant (default from env) log_name: Log file to read (default "job-output.txt") mode: "summary" (tail + errors), "errors" (errors only, no tail), or "full" (paginated) lines: For summary: tail count (default 50). For full: offset start line. start_line: Read from this line (1-based, overrides mode with end_line) end_line: Read up to this line (1-based, inclusive) grep: Regex to filter lines (overrides mode). Use | for OR. context: Lines of context around grep matches (default 0, max 10) url: Zuul build URL (alternative to uuid + tenant) direct_log_url: Log URL from a prior get_build/diagnose_build call. Skips the build metadata fetch when provided. max_matches: Max grep matches to return (default 50, max 200) filter_noise: Filter out noise lines (failed=0, RETRYING) from grep results (default true)

Browse or fetch files from a build's log directory.

Without path: lists top-level. With trailing '/': lists subdirectory. With file path: fetches content (max 512KB). For filtered reads, use get_build_log with grep instead.

Args: uuid: Build UUID tenant: Tenant (default from env) path: Relative path within the log dir (e.g. "logs/controller/") url: Zuul build URL (alternative to uuid + tenant) max_lines: Limit file content to first N lines (0 = no limit) direct_log_url: Log URL from a prior call. Skips build metadata fetch.

Get the last N lines of a build log — fastest way to see why a build failed.

More token-efficient than get_build_log(mode="summary") when you just need the tail.

Args: uuid: Build UUID tenant: Tenant (default from env) lines: Lines from the end (default 50, max 500) log_name: Log file to read (default "job-output.txt") url: Zuul build URL (alternative to uuid + tenant) skip_postrun: Tail from run phase end, skipping post-run (default true) direct_log_url: Log URL from a prior call. Skips build metadata fetch.

List all Zuul tenants with project and queue counts.

Live pipeline status showing what's currently queued/running.

Args: tenant: Tenant (default from env) pipeline: Pipeline name filter project: Project filter active_only: Only show pipelines with active items (default true)

Pipeline status for a specific change or PR/MR.

When in pipeline: live status with jobs, elapsed times, buildset UUID. When not in pipeline: fetches latest completed buildset automatically.

Args: change: Change number, GitHub ref (refs/pull/N/head), or GitLab ref tenant: Tenant (default from env) url: Zuul change status URL (alternative to change + tenant) brief: Strip to monitoring essentials (~75% smaller). Use for repeated polls.

Detect flaky jobs by analyzing recent build history for intermittent failures.

Computes pass/fail statistics from recent builds. A job with mixed results and >20% failure rate is likely flaky.

Args: job_name: Job name to analyze tenant: Tenant (default from env) project: Project filter pipeline: Pipeline filter limit: Builds to analyze (default 20, max 100) detail: Include individual build list (default false)

Build duration trends — compute avg/min/max to detect performance regressions.

Returns ALL results (no result filtering). For SUCCESS-only averages, use get_job_durations instead.

Args: tenant: Tenant (default from env) job_name: Job name filter project: Project filter pipeline: Pipeline filter branch: Branch filter limit: Max results, 1-100 (default 20) skip: Pagination offset detail: Include individual build list (default true)

Get avg/min/max duration for multiple jobs in a single call.

Fetches build history per job in parallel. Designed for monitoring tools that need durations for an entire pipeline chain.

Args: job_names: List of job names to get stats for tenant: Tenant (default from env) result: Result filter (default "SUCCESS" for clean averages) limit: Builds per job to analyze (default 10, max 50)

Test Zuul API connectivity and auth status.

Use this to verify the server is reachable. Re-auth happens automatically via Kerberos if the session expired.

Parse JUnit XML test results from a build's log directory.

Discovers test result files via zuul-manifest.json. Works with tempest, tobiko, and any JUnit XML output.

Args: uuid: Build UUID tenant: Tenant (default from env) url: Zuul build URL (alternative to uuid + tenant) failures_only: Only return suites with failures (default true)