Summary
Connects to the Buildkite API to surface your CI/CD data directly in Claude. You get access to pipelines, builds, jobs, and test analytics without switching contexts. Useful when debugging failing builds, investigating flaky tests, or checking deployment status during development conversations. The server runs in a container built on Chainguard's minimal static image for security. Buildkite maintains this officially, so it tracks their API changes. If you're already using Buildkite for CI/CD and want your AI assistant to help troubleshoot pipeline issues or query build history, this bridges that gap cleanly.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Tools
Public tool metadata for what this MCP can expose to an agent.
33 tools
access_tokenGet information about the current API access token including its scopes and UUID
Get information about the current API access token including its scopes and UUID
No parameter schema in public metadata yet.
create_buildTrigger a new build on a Buildkite pipeline for a specific commit and branch, with optional environment variables, metadata, and author information8 params
Trigger a new build on a Buildkite pipeline for a specific commit and branch, with optional environment variables, metadata, and author information
Parameters* required
branchstringcommitstringThe commit SHA to build
environmentarrayEnvironment variables to set for the build
ignore_branch_filtersbooleanWhether to ignore branch filters when triggering the build
messagestringmetadataarrayMeta-data values to set for the build
org_slugstringpipeline_slugstringcreate_clusterCreate a new cluster in an organization5 params
Create a new cluster in an organization
Parameters* required
colorstringHex color code for the cluster (e.g. #A9CCE3)
descriptionstringDescription of the cluster
emojistringEmoji for the cluster (e.g. :toolbox:)
namestringorg_slugstringcreate_cluster_queueCreate a new queue in a cluster4 params
Create a new queue in a cluster
Parameters* required
cluster_idstringdescriptionstringDescription of the queue
keystringorg_slugstringcreate_pipelineSet up a new CI/CD pipeline in Buildkite with YAML configuration, repository connection, and cluster assignment11 params
Set up a new CI/CD pipeline in Buildkite with YAML configuration, repository connection, and cluster assignment
Parameters* required
cancel_running_branch_buildsbooleanCancel running builds when new builds are created on the same branch
cluster_idstringThe cluster ID to assign the pipeline to
configurationstringThe pipeline configuration in YAML format
create_webhookbooleanCreate a GitHub webhook to trigger builds on pull-request and push events
default_branchstringThe default branch for builds and metrics filtering
descriptionstringnamestringorg_slugstringrepository_urlstringThe Git repository URL
skip_queued_branch_buildsbooleanSkip intermediate builds when new builds are created on the same branch
tagsarrayTags to apply to the pipeline for filtering and organization
current_userGet details about the user account that owns the API token, including name, email, avatar, and account creation date
Get details about the user account that owns the API token, including name, email, avatar, and account creation date
No parameter schema in public metadata yet.
get_artifactGet detailed information about a specific artifact including its metadata, file size, SHA-1 hash, and download URL1 params
Get detailed information about a specific artifact including its metadata, file size, SHA-1 hash, and download URL
Parameters* required
urlstringget_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 tools6 params
Get 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
Parameters* required
build_numberstringdetail_levelstringResponse detail level: 'detailed' (default) or 'full'. Detailed includes job IDs/names/states; full includes complete job objects
include_agentbooleanInclude full agent details in job objects. When false (default)\, only agent.id is included
job_statestringFilter jobs by state. Comma-separated for multiple states (e.g.\, 'failed\,broken\,canceled')
org_slugstringpipeline_slugstringget_build_test_engine_runsGet test engine runs data for a specific build in Buildkite. This can be used to look up Test Runs.3 params
Get test engine runs data for a specific build in Buildkite. This can be used to look up Test Runs.
Parameters* required
build_numberstringorg_slugstringpipeline_slugstringget_clusterGet detailed information about a specific cluster including its name, description, default queue, and configuration2 params
Get detailed information about a specific cluster including its name, description, default queue, and configuration
Parameters* required
cluster_idstringorg_slugstringget_cluster_queueGet detailed information about a specific queue including its key, description, dispatch status, and hosted agent configuration3 params
Get detailed information about a specific queue including its key, description, dispatch status, and hosted agent configuration
Parameters* required
cluster_idstringorg_slugstringqueue_idstringget_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.6 params
Get 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.
Parameters* required
include_failure_expandedbooleanInclude expanded failure details such as full error messages and stack traces
org_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
run_idstringtest_suite_slugstringget_pipelineGet detailed information about a specific pipeline including its configuration, steps, environment variables, and build statistics3 params
Get detailed information about a specific pipeline including its configuration, steps, environment variables, and build statistics
Parameters* required
detail_levelstringResponse detail level: 'summary'\, 'detailed'\, or 'full' (default)
org_slugstringpipeline_slugstringget_testGet a specific test in Buildkite Test Engine. This provides additional metadata for failed test executions3 params
Get a specific test in Buildkite Test Engine. This provides additional metadata for failed test executions
Parameters* required
org_slugstringtest_idstringtest_suite_slugstringget_test_runGet a specific test run in Buildkite Test Engine3 params
Get a specific test run in Buildkite Test Engine
Parameters* required
org_slugstringrun_idstringtest_suite_slugstringlist_annotationsList all annotations for a build, including their context, style (success/info/warning/error), rendered HTML content, and creation timestamps5 params
List all annotations for a build, including their context, style (success/info/warning/error), rendered HTML content, and creation timestamps
Parameters* required
build_numberstringorg_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
pipeline_slugstringlist_artifacts_for_buildList all artifacts for a build across all jobs, including file details, paths, sizes, MIME types, and download URLs5 params
List all artifacts for a build across all jobs, including file details, paths, sizes, MIME types, and download URLs
Parameters* required
build_numberstringorg_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
pipeline_slugstringlist_artifacts_for_jobList all artifacts for an individual job, including file details, paths, sizes, MIME types, and download URLs6 params
List all artifacts for an individual job, including file details, paths, sizes, MIME types, and download URLs
Parameters* required
build_numberstringjob_idstringorg_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
pipeline_slugstringlist_buildsList builds for a pipeline or across all pipelines in an organization. When pipeline_slug is omitted, lists builds across all pipelines in the organization9 params
List builds for a pipeline or across all pipelines in an organization. When pipeline_slug is omitted, lists builds across all pipelines in the organization
Parameters* required
branchstringFilter builds by git branch name
commitstringFilter builds by specific commit SHA
creatorstringFilter builds by build creator
detail_levelstringResponse detail level: 'summary' (default)\, 'detailed'\, or 'full'
org_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
pipeline_slugstringFilter builds by pipeline. When omitted\, lists builds across all pipelines in the organization
statestringFilter builds by state (scheduled\, running\, passed\, failed\, canceled\, skipped)
list_cluster_queuesList all queues in a cluster with their keys, descriptions, dispatch status, and agent configuration4 params
List all queues in a cluster with their keys, descriptions, dispatch status, and agent configuration
Parameters* required
cluster_idstringorg_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
list_clustersList all clusters in an organization with their names, descriptions, default queues, and creation details3 params
List all clusters in an organization with their names, descriptions, default queues, and creation details
Parameters* required
org_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
list_pipelinesList all pipelines in an organization with their basic details, build counts, and current status6 params
List all pipelines in an organization with their basic details, build counts, and current status
Parameters* required
detail_levelstringResponse detail level: 'summary' (default)\, 'detailed'\, or 'full'
namestringFilter pipelines by name
org_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
repositorystringFilter pipelines by repository URL
list_test_runsList all test runs for a test suite in Buildkite Test Engine4 params
List all test runs for a test suite in Buildkite Test Engine
Parameters* required
org_slugstringpageintegerPage number for pagination (min 1)
per_pageintegerResults per page for pagination (min 1\, max 100)
test_suite_slugstringpause_cluster_queue_dispatchPause dispatch on a cluster queue, preventing new jobs from being dispatched to agents4 params
Pause dispatch on a cluster queue, preventing new jobs from being dispatched to agents
Parameters* required
cluster_idstringnotestringReason for pausing dispatch
org_slugstringqueue_idstringread_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 fo...8 params
Read 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 fo...
Parameters* required
build_numberstringcache_ttlstringforce_refreshbooleanjob_idstringlimitintegerorg_slugstringpipeline_slugstringseekintegerresume_cluster_queue_dispatchResume dispatch on a paused cluster queue, allowing jobs to be dispatched to agents again3 params
Resume dispatch on a paused cluster queue, allowing jobs to be dispatched to agents again
Parameters* required
cluster_idstringorg_slugstringqueue_idstringsearch_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}.15 params
Search 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}.
Parameters* required
after_contextintegerbefore_contextintegerbuild_numberstringcache_ttlstringcase_sensitivebooleancontextintegerforce_refreshbooleaninvert_matchbooleanjob_idstringlimitintegerorg_slugstringpatternstringpipeline_slugstringreversebooleanseek_startintegertail_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}.7 params
Show 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}.
Parameters* required
build_numberstringcache_ttlstringforce_refreshbooleanjob_idstringorg_slugstringpipeline_slugstringtailintegerunblock_jobUnblock a blocked job in a Buildkite build to allow it to continue execution5 params
Unblock a blocked job in a Buildkite build to allow it to continue execution
Parameters* required
build_numberstringfieldsobjectJSON object containing string values for block step fields
job_idstringorg_slugstringpipeline_slugstringupdate_clusterUpdate an existing cluster's name, description, emoji, color, or default queue7 params
Update an existing cluster's name, description, emoji, color, or default queue
Parameters* required
cluster_idstringcolorstringNew hex color code for the cluster
default_queue_idstringID of the default queue for the cluster
descriptionstringNew description for the cluster
emojistringNew emoji for the cluster
namestringNew name for the cluster
org_slugstringupdate_cluster_queueUpdate an existing cluster queue's description or retry agent affinity5 params
Update an existing cluster queue's description or retry agent affinity
Parameters* required
cluster_idstringdescriptionstringNew description for the queue
org_slugstringqueue_idstringretry_agent_affinitystringAgent retry affinity: prefer-warmest or prefer-different
update_pipelineModify an existing Buildkite pipeline's configuration, repository, settings, or metadata11 params
Modify an existing Buildkite pipeline's configuration, repository, settings, or metadata
Parameters* required
cancel_running_branch_buildsbooleanCancel running builds when new builds are created on the same branch
cluster_idstringconfigurationstringThe pipeline configuration in YAML format
default_branchstringThe default branch for builds and metrics filtering
descriptionstringnamestringorg_slugstringpipeline_slugstringrepository_urlstringThe Git repository URL
skip_queued_branch_buildsbooleanSkip intermediate builds when new builds are created on the same branch
tagsarrayTags to apply to the pipeline for filtering and organization
user_token_organizationGet the organization associated with the user token used for this request
Get the organization associated with the user token used for this request
No parameter schema in public metadata yet.
buildkite-mcp-server
Model Context Protocol (MCP) server exposing Buildkite data (pipelines, builds, jobs, tests) to AI tooling and editors.
Full documentation is available at buildkite.com/docs/apis/mcp-server.
Library Usage
The exported Go API of this module should be considered unstable, and subject to breaking changes as we evolve this project.
Security
To ensure the MCP server is run in a secure environment, we recommend running it in a container.
This image is built from cgr.dev/chainguard/static and runs as an unprivileged user.
Passing identity headers through HTTP mode
Self-hosted HTTP deployments can forward selected headers from each inbound MCP request to the Buildkite API:
BUILDKITE_API_TOKEN=bkua_xxx \
buildkite-mcp-server http \
--passthrough-http-header X-User-Identity
Repeat --passthrough-http-header to allow more than one header, or set a comma-separated BUILDKITE_PASSTHROUGH_HTTP_HEADERS value. Only explicitly allowed headers are forwarded, and only to the origin configured by BUILDKITE_BASE_URL. They are removed from requests redirected elsewhere.
To authenticate each MCP request with its own Buildkite API token, allow Authorization and omit the process-wide token:
BUILDKITE_PASSTHROUGH_HTTP_HEADERS=Authorization \
buildkite-mcp-server http
In this mode every /mcp request must contain exactly one non-empty Authorization header. Missing credentials return HTTP 401; the server never falls back to a shared API token. The reverse proxy in front of the MCP server is responsible for authenticating callers and setting or validating any forwarded identity headers.
Header passthrough is not available in stdio mode. Before serving job logs, the server verifies that the current caller can access the job log. This check is performed for every log-tool request, including when the log data is already cached.
Contributing
Development guidelines are in DEVELOPMENT.md.
License
MIT © Buildkite
SPDX-License-Identifier: MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Configuration
BUILDKITE_API_TOKEN*secretBuildkite API token for authentication. Get one from https://buildkite.com/user/api-access-tokens
Categories
Registryactive
Packageghcr.io/buildkite/buildkite-mcp-server:0.7.0
TransportSTDIO
AuthRequired
UpdatedOct 10, 2025
