How to Use the Drone CI MCP in OpenAI Agents SDK

Q: How do I connect Drone CI to my OpenAI Agents SDK pipeline?

Install the package with pip install openai-agents. Initialize the MCP client with your Vinkius endpoint and pass it to the Agent constructor. The agent auto-discovers all 39 tools instantly.

Q: How does the OpenAI Agents SDK handle failed Drone CI builds?

The agent polls the build status using getbuild and fetches the failure logs with getbuildlogs. It analyzes the stack trace to determine if the failure is transient. If it is, the agent triggers restartbuild automatically.

Q: How do I handle cron jobs with this integration?

You configure the agent to manage scheduled tasks using createcronjob and updatecronjob. The agent can also trigger these tasks out of band using triggercronjob when external systems signal a dependency is ready.

Build production-ready Python agents that control your Drone CI pipelines with built-in guardrails via the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Drone CI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Drone CI to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Drone CI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run build lifecycles using OpenAI Agents SDK

`create_build` kicks off custom builds for any branch when your OpenAI Agents SDK agent detects a merged pull request. The agent monitors the pipeline status, using `get_build` to inspect stages and steps in real-time. If a step hangs or fails, the agent calls `restart_build` or `stop_build` to keep your runners clear. This setup avoids manual intervention during routine deployments. The agent executes these actions through the MCP Server, keeping your team updated on Slack or Discord. You get full execution logs without opening the Drone UI.

Manage secrets and templates with strict guardrails

`create_secret` writes sensitive variables directly to your repositories without exposing them in git history. Your agent uses `update_secret` and `delete_secret` to rotate credentials on a schedule. This removes the risk of stale API keys sitting in old repositories. OpenAI Agents SDK provides built-in validation before executing these sensitive actions. The agent verifies the repository context using `get_repo` before modifying any configuration. This prevents accidental changes to production environments.

Automated pipeline promotions and approvals

`promote_build` pushes successful builds to staging or production environments based on your deployment rules. If a pipeline requires manual intervention, the agent uses `approve_build` or `decline_build` to resolve the blocker. This gives your agent the ability to manage the entire release flow through a secure MCP connection. You configure handoffs between specialized agents to handle different stages of the release. One agent monitors logs using `get_build_logs`, while another handles the promotion step. This isolation keeps your production environment secure.

Setup guide

Set up Drone CI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Drone CI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Drone CI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Drone CI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Drone CI Agent",
            instructions="You have access to Drone CI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Drone CI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Drone CI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Drone CI MCP in OpenAI Agents SDK

Install the package with `pip install openai-agents`. Initialize the MCP client with your Vinkius endpoint and pass it to the Agent constructor. The agent auto-discovers all 39 tools instantly.

Yes, you control tool exposure at the SDK level. You can filter out admin-only tools like `create_user` or `delete_user` to ensure the agent only interacts with repositories. This limits the agent's blast radius.

The agent polls the build status using `get_build` and fetches the failure logs with `get_build_logs`. It analyzes the stack trace to determine if the failure is transient. If it is, the agent triggers `restart_build` automatically.

You configure the agent to manage scheduled tasks using `create_cron_job` and `update_cron_job`. The agent can also trigger these tasks out of band using `trigger_cron_job` when external systems signal a dependency is ready.

Your secrets and repository configuration data remain completely private. Vinkius runs the MCP Server in an isolated V8 sandbox, ensuring your environment variables and repository configuration data never persist. The server only handles active API transactions during tool execution, keeping your credentials secure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript