How to Use the Dagger (Programmable CI) MCP in OpenAI Agents SDK

Run your CI pipelines directly inside OpenAI Agents SDK. Build production-ready workflows with typed, validated Dagger operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dagger (Programmable CI) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Dagger (Programmable 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 Dagger (Programmable CI) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute GraphQL queries in OpenAI Agents SDK

Run complex build logic by piping your intent into `execute_graphql_query`. You define the graph and the engine handles the execution flow without leaving your agent context. This keeps your build logic inside your codebase. The agent handles the wiring, ensuring your DAG stays consistent across every deployment run.

Manage secrets and containers via Dagger (Programmable CI)

Use `query_secret` to inject environment variables or file paths into your pipeline safely. Your agent pulls these values at runtime, keeping sensitive keys out of your logs. Pair this with `query_container` to spawn isolated environments on the fly. You get a clean container ID every time, preventing state pollution between test steps.

Track build versions and modules

Check the exact engine state using `query_version`. Your agent knows exactly which Dagger build environment it is talking to before sending heavy tasks. `query_current_module` lets your agent inspect the local project structure. It reads the module context to ensure you never run build steps against the wrong directory.

Setup guide

Set up Dagger (Programmable 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 Dagger (Programmable CI) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dagger (Programmable 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 Dagger (Programmable 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="Dagger (Programmable CI) Agent",
            instructions="You have access to Dagger (Programmable 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 Dagger. 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 Dagger (Programmable 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 Dagger (Programmable CI) MCP in OpenAI Agents SDK

Yes, you connect the server directly to your agent constructor. The tools are auto-discovered, allowing your agent to trigger builds as part of its standard task sequence.

The server returns structured output for every query. If a build step fails, your agent receives the exact engine error, letting it retry or report the issue immediately.

Absolutely, all tool calls are logged through your dashboard. You see every GraphQL query and container spin-up event alongside your agent's decision-making process.

Vinkius manages the endpoint authentication for you. Your agent communicates over an encrypted channel, keeping your secret definitions isolated from the public internet.

The server only interacts with your CI configuration, build artifacts, and secret paths. It never reads your personal agent chat history or non-relevant project files.

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