How to Use the Drone CI MCP in AutoGen

Q: How do I register Drone CI MCP Server tools with my AutoGen assistant?

Use the mcpservertools helper from the AutoGen extension package to load the schema, then pass the tools directly to your AssistantAgent constructor.

Let specialized AutoGen agents debate and coordinate your Drone CI releases with full consensus.

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 AutoGen

Create your Vinkius account to connect Drone CI to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Release Management

This MCP Server provides the operational tools like `approve_build` and `decline_build` for multi-agent validation workflows. A QA agent can analyze test coverage while a security agent checks dependency vulnerability logs before they agree to release. Once both agents reach a consensus, the supervisor agent calls `approve_build` to unblock the pipeline. This eliminates single-point-of-failure human approvals while maintaining strict quality gates.

Collaborative Secret Lifecycle Control

The `create_secret` and `update_secret` tools allow coordinate agents to manage build credentials collaboratively. A security auditor agent detects expiring keys and requests a rotation, prompting a runner agent to generate and apply the new secret. Before updating, the agents verify the target using `list_secrets` to ensure they don't overwrite critical production keys. The entire negotiation and execution happen in a structured chat thread managed by the MCP Server.

AutoGen Multi-Agent Repository Provisioning

Using `enable_repo` and `chown_repo`, your provisioning agents can onboard new projects without manual admin intervention. An engineering agent requests a new pipeline, and the admin agent verifies the request before configuring the repository. The agents use `update_repo` to apply standard branch protection rules and webhook settings. This ensures every new repository in your organization matches your security baseline from day one.

Setup guide

Set up Drone CI MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Drone CI tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Drone CI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Drone CI data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Drone CI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Drone CI data")
    print(result.messages[-1].content)

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 AutoGen

One agent identifies a new commit, a security agent validates the changes, and they agree to call `create_build` to start the execution.

Yes. If the testing agent finds critical failures in the logs, it communicates the issue to the release agent, which then executes `decline_build`.

Use the `mcp_server_tools` helper from the AutoGen extension package to load the schema, then pass the tools directly to your `AssistantAgent` constructor.

The pipeline remains blocked. The build is only promoted via `promote_build` once all participating agents resolve their debate and reach a positive consensus.

The actual values of your secrets are never exposed to the LLM during operations like `create_secret` or `update_secret`. The MCP server handles the write operations securely, ensuring sensitive credentials never enter the agent conversation logs.

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