How to Use the Drone CI MCP in Google ADK

Q: How do I set up the Drone CI MCP Server with Google ADK?

Install the SDK via pip install google-adk and configure the McpToolset with your Vinkius HTTP URL. Pass this toolset to your LlmAgent to expose the Drone CI endpoints. Gemini will immediately begin using the tools.

Q: Can my Google ADK agent trigger production deployments through Drone CI?

Yes, the agent can invoke promotebuild to deploy artifacts to target environments. We recommend using the toolnames filter in Google ADK to restrict this capability to staging environments unless you have human-in-the-loop approvals configured.

Q: Can my agent manage organization templates?

Yes, the agent uses listtemplates, createtemplate, and updatetemplate to manage shared pipeline configurations. This ensures all new repositories use approved corporate build steps.

Q: How does the Google ADK integration protect my secrets?

All sensitive actions like createsecret and updatesecret bypass local storage entirely. The MCP Server executes these commands over an encrypted channel directly to your Drone instance. Your raw repository secrets are never cached or logged by Vinkius.

Connect Gemini's 1M token context window to your Drone CI pipelines using the Google ADK for enterprise automation.

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 Google ADK

Create your Vinkius account to connect Drone CI to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Gemini analyze entire build logs

`get_build_logs` pulls raw build output from failed steps directly into the Google ADK context window. Gemini parses thousands of lines of build logs instantly to pinpoint compiler errors or broken tests. It then suggests the exact code change needed to fix the build. This integration operates through the MCP Server to close the feedback loop. The agent can automatically trigger a new test run using `create_build` once the fix is applied. You stop wasting engineering hours scrolling through terminal outputs.

Enterprise repository management at scale

`sync_user_repos` updates the agent's map of your active projects across your entire version control system. The agent uses `enable_repo` and `disable_repo` to manage which projects are active in your CI system. This keeps your Drone dashboard clean and organized. For ownership transfers, the agent calls `chown_repo` to assign repositories to the correct system users. You maintain precise control over webhook configurations using `repair_repo` when paths change. This automation scales your platform engineering tasks without manual ticket queues.

Scheduled task management with Google ADK

`list_cron_jobs` lists active scheduled tasks across all your registered repositories. The agent uses `create_cron_job` and `update_cron_job` to align build schedules with your Google Cloud resource availability. This prevents runner queues from backing up during peak hours. If a data pipeline in BigQuery finishes early, the agent calls `trigger_cron_job` to start downstream testing. You build a dynamic CI workflow that responds to real-time data events.

Setup guide

Set up Drone CI MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Drone CI tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Drone CI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Drone CI tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the SDK via `pip install google-adk` and configure the `McpToolset` with your Vinkius HTTP URL. Pass this toolset to your `LlmAgent` to expose the Drone CI endpoints. Gemini will immediately begin using the tools.

Yes, the agent can invoke `promote_build` to deploy artifacts to target environments. We recommend using the `tool_names` filter in Google ADK to restrict this capability to staging environments unless you have human-in-the-loop approvals configured.

The MCP Server handles the authentication layer using your Vinkius endpoint token. You do not need to manage raw Drone API keys inside your Python agent code. Vinkius handles the secure handshake on every request.

Yes, the agent uses `list_templates`, `create_template`, and `update_template` to manage shared pipeline configurations. This ensures all new repositories use approved corporate build steps.

All sensitive actions like `create_secret` and `update_secret` bypass local storage entirely. The MCP Server executes these commands over an encrypted channel directly to your Drone instance. Your raw repository secrets are never cached or logged by Vinkius.

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