Buildkite
Manage [Buildkite](https://buildkite.com) pipelines and builds.
https://buildkite.run.tools
How to connect
-
Smithery (hosted)
1. Open https://smithery.ai/servers/buildkite 2. Click Connect and complete OAuth in your MCP client (Claude, Cursor, VS Code, etc.) 3. MCP endpoint: https://buildkite.run.tools
Tools (33)
-
access_tokenGet information about the current API access token including its scopes and UUID
-
create_buildTrigger a new build on a Buildkite pipeline for a specific commit and branch, with optional environment variables, metadata, and author information
-
create_clusterCreate a new cluster in an organization
-
create_cluster_queueCreate a new queue in a cluster
-
create_pipelineSet up a new CI/CD pipeline in Buildkite with YAML configuration, repository connection, and cluster assignment
-
current_userGet details about the user account that owns the API token, including name, email, avatar, and account creation date
-
get_artifactGet detailed information about a specific artifact including its metadata, file size, SHA-1 hash, and download URL
-
get_buildGet build information including job IDs, names, and states. Use job_state to filter (e.g. 'failed,broken'). Returns enough detail to identify which jobs to investigate with log and artifact tools
-
get_build_test_engine_runsGet test engine runs data for a specific build in Buildkite. This can be used to look up Test Runs.
-
get_clusterGet detailed information about a specific cluster including its name, description, default queue, and configuration
-
get_cluster_queueGet detailed information about a specific queue including its key, description, dispatch status, and hosted agent configuration
-
get_failed_executionsGet failed test executions for a specific test run in Buildkite Test Engine. Optionally get the expanded failure details such as full error messages and stack traces.
-
get_pipelineGet detailed information about a specific pipeline including its configuration, steps, environment variables, and build statistics
-
get_testGet a specific test in Buildkite Test Engine. This provides additional metadata for failed test executions
-
get_test_runGet a specific test run in Buildkite Test Engine
-
list_annotationsList all annotations for a build, including their context, style (success/info/warning/error), rendered HTML content, and creation timestamps
-
list_artifacts_for_buildList all artifacts for a build across all jobs, including file details, paths, sizes, MIME types, and download URLs
-
list_artifacts_for_jobList all artifacts for an individual job, including file details, paths, sizes, MIME types, and download URLs
-
list_buildsList builds for a pipeline or across all pipelines in an organization. When pipeline_slug is omitted, lists builds across all pipelines in the organization
-
list_cluster_queuesList all queues in a cluster with their keys, descriptions, dispatch status, and agent configuration
-
list_clustersList all clusters in an organization with their names, descriptions, default queues, and creation details
-
list_pipelinesList all pipelines in an organization with their basic details, build counts, and current status
-
list_test_runsList all test runs for a test suite in Buildkite Test Engine
-
pause_cluster_queue_dispatchPause dispatch on a cluster queue, preventing new jobs from being dispatched to agents
-
read_logsRead log entries from the file, optionally starting from a specific row number. ALWAYS use 'limit' parameter to avoid excessive tokens. For recent failures, use 'tail_logs' instead. Recommended limits: investigation (100-500), exploration (use seek + small limits). The json format: {ts: timestamp_ms, c: content, rn: row_number}.
-
resume_cluster_queue_dispatchResume dispatch on a paused cluster queue, allowing jobs to be dispatched to agents again
-
search_logsSearch log entries using regex patterns with optional context lines. For recent failures, try 'tail_logs' first, then use search_logs with patterns like 'error|failed|exception' and limit: 10-20. The json format: {ts: timestamp_ms, c: content, rn: row_number}.
-
tail_logsShow the last N entries from the log file. RECOMMENDED for failure diagnosis - most build failures appear in the final log entries. More token-efficient than read_logs for recent issues. The json format: {ts: timestamp_ms, c: content, rn: row_number}.
-
unblock_jobUnblock a blocked job in a Buildkite build to allow it to continue execution
-
update_clusterUpdate an existing cluster's name, description, emoji, color, or default queue
-
update_cluster_queueUpdate an existing cluster queue's description or retry agent affinity
-
update_pipelineModify an existing Buildkite pipeline's configuration, repository, settings, or metadata
-
user_token_organizationGet the organization associated with the user token used for this request