Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Buildkite in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Check Buildkite from your AI agent: pipelines, builds and jobs, job logs, artifacts and annotations, agents, clusters and queues, and Test Engine suites with flaky and slow tests, and start, rebuild and retry builds, unblock steps and add annotations after you confirm.
Try asking
Example prompts for Buildkite
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Buildkite, paste your credentials, mint an MCP API key and you're done. No Docker, no
git clone, no local server.
Buildkite
Check Buildkite from your AI agent: pipelines, builds and jobs, job logs, artifacts and annotations, agents, clusters and queues, and Test Engine suites with flaky and slow tests, and start, rebuild and retry builds, unblock steps and add annotations after you confirm.
Setup
Setting up takes about 3 minutes. You need a Buildkite account with access to the organization.
- In Buildkite open your avatar, Personal Settings, API Access Tokens (https://buildkite.com/user/api-access-tokens) and click New API Access Token.
- Choose the organizations and these scopes:
read_builds,read_build_logs,read_pipelines,read_artifacts,read_agents,read_clusters,read_organizations,read_userand, for Test Engine,read_suites. For the writes addwrite_builds. Leave out whatever you do not want the AI to do. - Paste the token (it usually starts with
bkua_) intoBUILDKITE_API_TOKEN. It is sent asAuthorization: Bearer <token>to api.buildkite.com only, and the AI acts as the user who owns it. - Install the connector and run
buildkite_get_access_token: it shows the token's scopes. Thenbuildkite_list_organizationslists the organization slugs.
Slugs and numbers: tools take the organization slug (org) and the pipeline slug (pipeline) as in buildkite.com/<org>/<pipeline>, and the build number (#123), not the build UUID. Jobs, artifacts and agents use UUIDs. buildkite_list_test_runs filters by the build UUID (the id of the build).
What it reads:
- Organizations and pipelines:
buildkite_get_current_user,buildkite_list_organizations,buildkite_get_organization,buildkite_list_pipelines(filter by part of the name or repository URL) andbuildkite_get_pipelinewith repository, default branch, branch filters, cluster and the YAML steps. - Builds:
buildkite_list_buildsfor the whole organization orbuildkite_list_pipeline_buildsfor one pipeline, newest first, filtered by branch, state (failed,running,blockedand more), commit, creator or dates. They leave the jobs out by default;buildkite_get_buildshows them with state, exit status, step key and agent. - Why a build failed:
buildkite_list_jobswithstateset to failed, thenbuildkite_get_jobandbuildkite_get_job_log, which returns the end of the log as plain text, by default the last 100,000 bytes where the error usually is (tail_bytesup to 5,000,000).buildkite_list_annotationsoften holds the test or coverage summary. - Artifacts:
buildkite_list_build_artifacts,buildkite_list_job_artifacts(filter by state or path glob) andbuildkite_get_artifactwith size, mime type, sha1 and the download URL; the file itself opens in the Buildkite app. - Agents and capacity:
buildkite_list_agents(hostname, version, queue, tags, connection state, current job),buildkite_get_agent,buildkite_list_clusters,buildkite_get_clusterandbuildkite_list_cluster_queues(whether dispatch is paused). - Test Engine:
buildkite_list_test_suites,buildkite_list_testswith reliability, durations, execution counts, labels such as flaky and owners (sort_by=reliabilitywithorder=ascfor the least reliable),buildkite_get_testwith flakiness scores,buildkite_list_test_runs,buildkite_get_test_runandbuildkite_list_failed_executionswith failure reason and, on request, the backtrace.
What it changes, after you confirm: buildkite_create_build (pipeline, commit, branch, message, environment), buildkite_rebuild_build, buildkite_retry_failed_jobs, buildkite_retry_job, buildkite_unblock_job and buildkite_create_annotation. Builds run real steps on your agents, including deployments, and use compute, so the AI names the pipeline, build and branch and waits for your yes. buildkite_unblock_job approves a manual gate, often the one before production: the AI calls it only when you explicitly say so.
Switched off at install: buildkite_cancel_build. A canceled build stops its running jobs, can leave a deployment half done and cannot be resumed, only rebuilt, so a workspace admin turns it on when the team needs it.
Data formats: states are lower case (passed, failed, running, blocked, canceled). Times are ISO 8601 in UTC. web_url opens the build or job in Buildkite. Log lines can contain ANSI colour codes. Test durations are in seconds, and reliability is a fraction (0.95 = 95%).
Paging: list tools take page and per_page (default 30, up to 100). When there are more results the answer carries _pagination.nextUrl; the AI asks for the next page (or passes after for buildkite_list_jobs) until _pagination is missing. Very deep build listings answer 400; the AI then narrows them with branch or created_from.
Limits: Buildkite limits REST calls per organization and per user per minute and answers 429 when either is used up; wait the seconds in RateLimit-Reset and try again.
Common errors: 401 means the token is wrong, expired or revoked. 403 means the token lacks the scope for the call (check with buildkite_get_access_token) or has no access to that organization. 404 means a wrong slug, number or id. 422 explains why a build or job cannot be created, retried or unblocked.
The connector does not read job environment variables (they hold secrets), does not delete logs, artifacts, annotations or pipelines, does not create or change pipelines, clusters, queues or agent tokens, does not stop or pause agents, and does not handle teams, members, audit events, package registries or test state changes such as mute and skip.
Prerequisites: BUILDKITE_API_TOKEN
Install the connector locally
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Open http://localhost:3000/connectors/store, pick Buildkite and paste in the env vars listed under Prerequisites.
Available tools
| Tool | What it does |
|---|---|
buildkite_get_access_token | Read the API access token in use: its scopes, description, expiry and owner |
buildkite_get_current_user | Read the Buildkite user the token belongs to: id, name, email and avatar |
buildkite_list_organizations | List the organizations the token can reach, with their slug, name and web URL |
buildkite_get_organization | Read one organization: name, slug, web URL and links to its pipelines and agents |
buildkite_list_pipelines | List the pipelines of an organization: slug, name, repository, default branch, cluster and running and scheduled build counts |
buildkite_get_pipeline | Read one pipeline: repository, default branch, branch filters, cluster, provider settings and its YAML steps configuration |
buildkite_list_builds | List the builds of a whole organization, newest first: number, state, branch, commit, message, creator, pipeline and times |
buildkite_list_pipeline_builds | List the builds of one pipeline, newest first, with the same filters as buildkite_list_builds |
buildkite_get_build | Read one build by its number: state, branch, commit, message, creator, times, job_state_counts and its jobs with state, exit status, step… |
buildkite_list_jobs | List the jobs of a build, optionally only some states or one step or group key: id, name, step key, state, exit status, agent and times |
buildkite_get_job | Read one job by id: name, command, state, exit status, signal, agent, retry information, times and web URL |
buildkite_get_job_log | Read the end of a job's log as plain text, by default the last 100,000 bytes, where the error usually is |
buildkite_list_build_artifacts | List the artifacts uploaded by all jobs of a build: id, job id, path, file size, mime type, state and sha1 |
buildkite_list_job_artifacts | List the artifacts of one job, with the same fields and filters as buildkite_list_build_artifacts |
buildkite_get_artifact | Read one artifact's metadata: path, size, mime type, state, sha1 and its download URL (the file itself opens in the Buildkite app) |
buildkite_list_annotations | List the annotations of a build: context, style (success, info, warning, error), priority and the rendered HTML body, often a test or… |
buildkite_list_agents | List the connected agents of an organization: id, name, hostname, version, queue, tags (meta_data), connection state and the job they run |
buildkite_get_agent | Read one agent by id, also a disconnected one: connection state, hostname, version, queue, tags, current job and times |
buildkite_list_clusters | List the clusters of an organization: id, name, description, default queue and maintainers |
buildkite_get_cluster | Read one cluster: name, description, default queue and maintainers |
buildkite_list_cluster_queues | List the queues of a cluster: id, key, description, hosted agent settings and whether dispatch is paused |
buildkite_list_test_suites | List the Test Engine suites of an organization: slug, name, default branch and web URL |
buildkite_list_tests | List the tests of a Test Engine suite with metrics over a time window: reliability, average and total duration, execution counts, labels… |
buildkite_get_test | Read one test of a suite with its duration, reliability and execution metrics and its flakiness scores over a time window |
buildkite_list_test_runs | List the test runs of a suite, newest first: id, branch, commit, result, execution counts by result and the build they belong to |
buildkite_get_test_run | Read one test run: state, result, branch, commit, execution counts and times |
buildkite_list_failed_executions | List the failed test executions of a run: test name and location, failure reason and, with include_failure_expanded, the expanded failure… |
buildkite_create_build | Start a new build of a pipeline for a commit and branch |
buildkite_rebuild_build | Run a finished build again as a new build with the same commit, branch and settings, including any deploy steps |
buildkite_retry_failed_jobs | Retry the failed jobs of a build in place, optionally only some failure kinds |
buildkite_retry_job | Retry one failed, timed out or canceled job; the retry runs as a new job in the same build |
buildkite_unblock_job | Unblock a block step (a manual approval, often before a deploy) so the build continues, optionally with values for the step's fields |
buildkite_create_annotation | Add an annotation (a Markdown or HTML note shown on the build page) to a build, or append to the one with the same context |
buildkite_cancel_build | Cancel a scheduled, running or failing build; its running jobs stop and the rest never run, which can leave a deployment half done |
Example prompts
- "Why did the last build of the api pipeline on main fail? Show me the error from the failed job's log."
- "Which builds are blocked right now waiting for an approval?"
- "List the 10 least reliable tests in our Test Engine suite over the last 7 days."
- "Retry the failed jobs of build #4821 in the web pipeline."
- "How many agents are connected in the default queue, and which of them are busy?"
Next steps
Was this guide helpful?