Buildkite MCP server for AI agents

This MCP server provides an interface for accessing Buildkite data through the Model Context Protocol, allowing AI tools and editors to seamlessly interact with your pipelines, builds, jobs, and tests.

Installation Options

Docker (Recommended)

First, create a Buildkite API token with the necessary permissions:

docker pull ghcr.io/buildkite/buildkite-mcp-server
docker run -it --rm -e BUILDKITE_API_TOKEN=bkua_xxxxx ghcr.io/buildkite/buildkite-mcp-server stdio

Pre-built Binary

Download the latest release from GitHub Releases. On macOS, you can use Homebrew:

brew install buildkite/buildkite/buildkite-mcp-server

Build from Source

go install github.com/buildkite/buildkite-mcp-server@latest
# or
goreleaser build --snapshot --clean
# or
make build    # uses goreleaser (snapshot)

API Token Scopes

Full Functionality

Create a token with the following scopes for complete access:

read_clusters - Access cluster & queue information
read_pipelines - Pipeline configuration
read_builds - Builds, jobs & annotations
read_build_logs - Job log output
read_user - Current user info
read_organizations - Organization details
read_artifacts - Build artifacts & metadata
read_suites - Buildkite Test Engine data

Minimum Recommended

At minimum, include these scopes:

read_builds - Builds, jobs & annotations
read_pipelines - Pipeline information
read_user - User identification

Configuration for Various Editors

Amp

Using Docker (recommended):

# ~/.config/amp/settings.json
{
  "amp.mcpServers": {
    "buildkite": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm", "-e", "BUILDKITE_API_TOKEN",
        "ghcr.io/buildkite/buildkite-mcp-server", "stdio"
      ],
      "env": { "BUILDKITE_API_TOKEN": "bkua_xxxxxxxx" }
    }
  }
}

Claude Code

Using Docker:

claude mcp add buildkite -- docker run --rm -i -e BUILDKITE_API_TOKEN=bkua_xxxxxxxx ghcr.io/buildkite/buildkite-mcp-server stdio

VS Code

{
  "inputs": [
    {
      "id": "BUILDKITE_API_TOKEN",
      "type": "promptString",
      "description": "Enter your Buildkite Access Token",
      "password": true
    }
  ],
  "servers": {
    "buildkite": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm", "-e", "BUILDKITE_API_TOKEN",
        "ghcr.io/buildkite/buildkite-mcp-server", "stdio"
      ],
      "env": { "BUILDKITE_API_TOKEN": "${input:BUILDKITE_API_TOKEN}" }
    }
  }
}

Zed

There is a Zed editor extension available in the official extension gallery. During installation, it will ask for an API token.

Alternatively, configure manually:

// ~/.config/zed/settings.json
{
  "context_servers": {
    "mcp-server-buildkite": {
      "settings": {
        "buildkite_api_token": "your-buildkite-token-here"
      }
    }
  }
}

Environment Variables

Variable	Description	Default	Usage
`BUILDKITE_API_TOKEN`	Your Buildkite API access token	Required	Authentication for all API requests
`JOB_LOG_TOKEN_THRESHOLD`	Token threshold for job logs	`0` (disabled)	Local installations only - Downloads logs to temp directory when exceeded

Job Log Token Threshold

This setting controls when large job logs are downloaded to your local temporary directory instead of being returned directly. It should only be used with local installations as it:

Downloads job logs to your system's temporary directory
Reads log files from disk instead of returning them in the response
May consume local disk space for large log files

Available Tools

The MCP server provides access to numerous Buildkite features:

Clusters and Queues: get_cluster, list_clusters, get_cluster_queue, list_cluster_queues
Pipelines: get_pipeline, list_pipelines, create_pipeline, update_pipeline
Builds: list_builds, get_build, get_build_test_engine_runs, create_build
Jobs and Artifacts: get_jobs, list_artifacts, get_artifact
Logs and Tests: search_logs, tail_logs, get_logs_info, read_logs, list_test_runs, get_test_run
User Information: current_user, user_token_organization, access_token

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "buildkite" '{"command":"docker","args":["run","-i","--rm","-e","BUILDKITE_API_TOKEN","ghcr.io/buildkite/buildkite-mcp-server","stdio"],"env":{"BUILDKITE_API_TOKEN":"bkua_xxxxxxxx"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "buildkite": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "BUILDKITE_API_TOKEN",
                "ghcr.io/buildkite/buildkite-mcp-server",
                "stdio"
            ],
            "env": {
                "BUILDKITE_API_TOKEN": "bkua_xxxxxxxx"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "buildkite": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "BUILDKITE_API_TOKEN",
                "ghcr.io/buildkite/buildkite-mcp-server",
                "stdio"
            ],
            "env": {
                "BUILDKITE_API_TOKEN": "bkua_xxxxxxxx"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect