# Buildkite (MCP Server)

> Inspect Buildkite pipelines, builds, logs and failures

- Type: MCP server
- Publisher: Buildkite (official)
- Categories: DevOps & Cloud, Development
- Website: https://buildkite.com/docs/apis/mcp-server
- Source: https://github.com/buildkite/buildkite-mcp-server
- Transport: streamable-http
- Server URL: https://mcp.buildkite.com/mcp
- Launch command: buildkite-mcp-server
- Sign-in: oauth
- Environment variables: BUILDKITE_API_TOKEN
- GitHub stars: 54
- Listed: 2025-05-01

## About

Buildkite's official MCP server exposes Buildkite pipelines, builds, jobs, logs and test data to AI tools. The remote server supports OAuth (with a read-only endpoint) or API-token pass-through; a local server/Docker image uses BUILDKITE_API_TOKEN.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.buildkite.com/mcp as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add buildkite --url https://mcp.buildkite.com/mcp
   codex mcp login buildkite
   ```

   config.toml:

   ```toml
   [mcp_servers.buildkite]
   url = "https://mcp.buildkite.com/mcp"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "buildkite",
           "server_url": "https://mcp.buildkite.com/mcp",
           "authorization": os.environ["BUILDKITE_API_TOKEN"],
           "require_approval": "never",
       }],
       input="Summarize why build #1234 on the web pipeline failed",
   )
   print(response.output_text)
   ```

## Tools

- `read_builds`
- `read_build_logs`
- `tail_logs`
- `get_build_failure_summary`
- `compare_builds`

## Example prompts

- "Summarize why build #1234 on the web pipeline failed"
- "Compare the last passing and failing builds"
- "Tail the logs for the running deploy job"
- "List recent builds on main"

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/buildkite · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.