The Model Context Protocol has gone stateless—and Buildkite is ready. The Buildkite MCP Server is now compliant with the MCP 2026-07-28 specification across both the open-source server and the Remote MCP Server. The headline change transforms MCP from a bidirectional, stateful protocol into a stateless request-response protocol. This was one of the most highly requested improvements from MCP devel…
The OpenTelemetry Notification Service now has a Request Log panel that is available in preview. This gives you more visibility into your trace exports and helps you diagnose connectivity, authentication, and endpoint configuration issues. The panel shows the last 20 outbound trace export requests. Each row shows the request UUID and exported span name (for example, buildkite.job or buildkite.step…
On 1 September 2026 (AEST), Buildkite Agent v4 becomes the stable release. From that date, installations and upgrades that follow the latest or stable release channels will use v4. We expect most customers to be unaffected. v4 retires functionality that has been deprecated for years and makes current, supported behaviour the default, giving the agent a cleaner baseline for what we build next. New…
Debugging a failed build shouldn't start with a scavenger hunt. The Buildkite MCP Server now includes get_build_failure_summary, a new tool designed around Anthropic's best practices for writing tools for agents. It turns a common multi-step workflow into one purpose-built call, taking an agent from “the build failed” to a likely cause. The tool brings together the build state, failed and broken j…
The Elastic CI Stack for AWS now supports Ubuntu 24.04 LTS as an alternative to Amazon Linux 2023 for Linux agents. Ubuntu images are available for both x86-64 and ARM64 instances. Ubuntu can be selected with either supported deployment method: For CloudFormation, set the LinuxDistribution parameter to ubuntu2404 in Elastic CI Stack for AWS v6.70.0. For Terraform, set linux_distribution = "ubuntu2…
The Buildkite MCP Server can now discover and load on-demand usage guides, and log searching is more efficient and reliable. Discoverable skill guides for agents Agents can now discover and load usage guides on demand, instead of relying solely on tool descriptions or the server's static instructions. Guides can be searched by keyword and loaded in full when needed, making it easier for an agent t…
Teams using GitLab.com or GitLab Self-Managed can now build merge requests and test proposed merges against their target branches with merged-results builds. Merge request builds test the source branch, while merged-results builds test the proposed merge, helping catch integration failures before merging. Set up merge request builds In your pipeline's GitLab settings: Enable Build merge requests t…
The Buildkite MCP Server now returns leaner job data by default and surfaces build annotations without extra round trips. Smaller, more targeted job listings list_jobs now returns compact, actionable summaries by default, reducing token usage while keeping job IDs and failure diagnostics. Use detail_level: "detailed" for execution metadata, or detail_level: "full" for the previous, more verbose re…
Test execution results uploaded to Test Engine are immutable, and so cannot be updated after initial upload. To allow metadata to be attached to execution records after upload we have introduced mutable tags. Additional tags can be attached to executions in bulk via the execution tags API endpoint. Mutable tags must use the reserved mut. prefix, and can be used in filters in the same way as immuta…
The REST API's List Jobs endpoint now accepts optional step_key and group_key filters. Use step_key to return the jobs for a specific step, including every job in a parallel step. Use group_key to return all jobs in a step group. These filters avoid fetching and filtering a build's full job list when you only need jobs from one step or group.
The Remote MCP Server's OAuth flow has had several reliability and security improvements, changing how MCP client sessions stay authenticated. Sessions refresh instead of expiring Previously, a session was tied to a fixed 7-day refresh token, after which an MCP client had to go through the full interactive authorization flow again. Sessions are now refreshed continuously in the background: access…
Organization administrators can now see when a user authorizes an OAuth application to access their organization in the Buildkite audit log. Each OAUTH_APPLICATION_AUTHORIZED event identifies the user, OAuth application, organization, granted scopes, request IP address, and User Agent. This provides a clearer record of when tools using OAuth—such as the Buildkite CLI and Remote MCP Server—are gran…
Retried jobs now show their previous attempts directly in the build list. Click the job, or expand it with the chevron, to inspect earlier attempts without leaving the page. We've heard from customers that it should be easier to see when jobs have been retried and quickly inspect what happened across attempts. This update makes it faster to compare retries, understand what changed, and debug flaky…
The Buildkite MCP Server has new tools for working with jobs, smarter artifact and log handling, and more scalable pagination for large builds and test runs. Dedicated tools for inspecting jobs Agents can now look up job details directly with list_jobs and get_job, filter by state (for example, only failed jobs), page through large builds efficiently, and pull full agent details only when needed.…
The outbound IP address ranges used by Hosted Agents are being updated. The updated ranges are now visible in your Cluster's Networking page, but will not take effect until August 2, 2026. The new, larger ranges provide additional IP address space to support increasing workloads. If you maintain IP allowlists or firewall rules, please review and update them before August 2 to ensure uninterrupted…
Buildkite's REST API now exposes more of the job and runner context that agents, CLI tools, and MCP clients need to tell infrastructure failures apart from code failures. The REST job object now includes signal and signal_reason. When signal_reason is present, it explains why the Buildkite Agent terminated the job, such as agent_stop or process_run_error. That gives automated debugging loops a cle…
Read-only API access tokens no longer return a pipeline's webhook_url in REST and GraphQL responses. Previously, a read_only token created by someone with pipeline write access could still retrieve the webhook_url. Because that URL can be used to trigger builds, a token intended to be read-only could effectively grant write access. Buildkite now checks both the token's scope and its creator's perm…
We've made a few improvements to the way log groups render on the new build page. For a running job, the log group that's currently running stays open and on screen, and we've added live durations and sticky headers to make it easier to follow along. See the duration of the running log group: The running log group now shows a ticking duration and a bar that grows in real time, instead of a spinner…
There's a new Metrics tab on every job that runs on Buildkite hosted agents, giving you a live view of how that job used its machine. No dashboards to wire up, no agent configuration — open a job and the charts are right there. Measure CPU load: See how hard the machine worked over the life of the job, so you can spot steps that are starved for CPU or right-size an oversized instance. Watch memory…
You can now fetch jobs separately from builds in the REST API, making large matrix or high-parallelism builds easier to query. List builds without embedded jobs: GET /v2/organizations/:org/pipelines/:pipeline/builds?exclude_jobs=true Then fetch only the jobs you need: # List jobs for one build, with filtering and pagination GET /v2/organizations/:org/pipelines/:pipeline/builds/:build/jobs?state[]=…
Checkout Skip checkout on any agent by setting BUILDKITE_SKIP_CHECKOUT=true — no plugin or workaround required. Previously this meant clearing BUILDKITE_REPO, using a checkout plugin, or (in the Agent Stack for Kubernetes) setting checkout: skip: true. Skip fetching commits you already have with --git-skip-fetch-existing-commits, which skips the git fetch step during checkout when the target commi…
A preview of Buildkite API access token authentication for the Buildkite Remote MCP Server is now available through a dedicated endpoint: https://mcp.buildkite.com/direct. Use this endpoint for headless or background agents that already have a Buildkite API access token and do not need the interactive OAuth flow. This helps avoid contention around shared OAuth tokens when multiple background agent…
The Buildkite MCP Server can now do more than read from Buildkite. It can take action across clusters, builds, jobs, and pipeline schedules. New cluster and queue management tools let agents list, inspect, create, and update Buildkite clusters and cluster queues, and pause or resume queue dispatch. These are gated behind the read_clusters and write_clusters toolsets. Agents can now cancel a runnin…
The metaData field on builds and jobs now supports up to 1 MB of total data, up from the previous 64 KB limit. If you've been hitting size constraints when attaching metadata to builds, this gives you significantly more room. Job annotations are now accessible through the GraphQL API. You can query annotations for any job, including the body content, context label, and annotation style, without ne…
You can now update a job's timeout at runtime using the new buildkite-agent job update command. If a job discovers mid-run that it needs more (or less) time, it can adjust its own timeout without requiring a pipeline change. $ buildkite-agent job update timeout 20 This sets the job's timeout to 20 minutes. You can also pipe the value from stdin: $ echo 20 | buildkite-agent job update timeout The c…