Buildkite for AI agents
Buildkite runs continuous integration pipelines on a team's own infrastructure, coordinating builds and agents while leaving the compute itself under the team's control. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Buildkite.
Check pipeline agent capacity
List the agents attached to a pipeline to see what capacity is free before queuing more builds.
Look up organization access
List the organizations tied to an access token to confirm which account a pipeline belongs to.
Verify the current token's user
Check which user and permissions a token maps to before running any pipeline changes.
5 Buildkite actions, graded by risk.
Every Buildkite action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- buildkite.get_metaGet Meta
- buildkite.get_userGet User
- buildkite.list_organizationsList Organizations
- buildkite.list_pipeline_agentsList Pipeline Agents
- buildkite.get_current_access_tokenGet Current Access Token
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Buildkite in three steps.
- 01Your users connect BuildkiteThey add their Buildkite api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Buildkite through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('buildkite', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Buildkite connects.
Users add their Buildkite api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Buildkite connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Buildkite from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Buildkite and Arc0, answered.
Can I use Buildkite with Claude, ChatGPT or Cursor?
Yes. Connect Buildkite to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Buildkite actions you allow.
How do users connect Buildkite?
Users add their Buildkite api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Buildkite actions can my agent take?
5 in total: 5 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Buildkite?
Yes. Allow read actions and deny writes in the Buildkite policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Buildkite too?
Yes. The same Buildkite connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Buildkite into your agent.
Your users connect Buildkite once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan