buildkite

Endpoint

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• access_token — Retrieve current API token information including scopes and UUID.
• current_user — Get user account details like name
• user_token_organization — Fetch Buildkite organization details for the token user.
• list_clusters — List all clusters with names
• get_cluster — Retrieve detailed information about a specific cluster.
• create_cluster — Establish a new cluster in an organization.
• update_cluster —
• list_cluster_queues — List all queues within a cluster.
• get_cluster_queue — Retrieve detailed queue information including dispatch status.
• create_cluster_queue — Create a new queue in a cluster.
• update_cluster_queue — Modify queue description or retry agent affinity.
• pause_cluster_queue_dispatch — Pause dispatch on a queue to prevent job assignment.
• resume_cluster_queue_dispatch — Resume dispatch on a paused queue.
• list_agents — List agents with connection state
• get_agent — Get detailed information about a specific agent.
• list_pipelines — List all organization pipelines with basic details and build counts.
• get_pipeline — Retrieve comprehensive pipeline configuration and statistics.
• create_pipeline — Set up a new CI/CD pipeline with YAML configuration.
• update_pipeline — Modify existing pipeline configuration and settings.
• list_pipeline_schedules — List pipeline schedules including cron expressions and next build time.
• get_pipeline_schedule — Retrieve specific schedule details with cron and branch info.
• create_pipeline_schedule — Create a cron-driven pipeline schedule.
• update_pipeline_schedule — Modify schedule cron
• list_builds — List builds for organization or pipeline with state
• get_build — Retrieve build metadata without jobs or expanded pipeline details.
• get_build_test_engine_runs — Get Test Engine runs data for a specific build.
• create_build — Trigger a new build on a pipeline for a specific commit.
• cancel_build — Cancel a running build.
• rebuild_build — Rebuild or retry an entire build.
• list_jobs — List jobs for a build with optional state filtering and pagination.
• get_job — Retrieve a job by UUID with full details.
• unblock_job — Unblock a blocked job to allow continuation.
• retry_job — Retry a failed or timed-out job.
• get_job_env — Retrieve environment variables for a specific job.
• search_logs — Search log entries using regex patterns with optional context lines.
• tail_logs — Show the last N entries from the log file.
• read_logs — Read log entries optionally starting from a specific row number.
• list_artifacts_for_build — List all build artifacts across jobs with file details.
• list_artifacts_for_job — List artifacts for a specific job.
• get_artifact — Download a specific artifact's content in base64 format.
• list_annotations — List annotations for a build or specific job.
• create_annotation — Create an annotation on a build or job.
• get_test — Retrieve a specific test with metadata for failed executions.
• list_test_runs — List all test runs for a suite.
• get_test_run — Retrieve a specific test run.
• get_failed_executions — Retrieve failed test executions with optional expanded failure details.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.