How to Use the Dagger (Programmable CI) MCP in CrewAI

Q: How do I configure Dagger (Programmable CI) for CrewAI?

Run pip install crewai "crewaitools" in your terminal. Pass the Vinkius endpoint directly into the mcps array on your agent definition for the MCP server. The framework handles the connection automatically.

Deploy autonomous CI/CD teams with CrewAI. Let specialized agents build, test, and ship code using Dagger.

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 CrewAI

Create your Vinkius account to connect Dagger (Programmable CI) to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent CI coordination in CrewAI

`execute_graphql_query` serves as the primary communication layer between your agents and the Dagger engine. A developer agent writes the build logic while a separate QA agent executes the DAG operations. They share memory context, meaning the tester knows exactly what the builder just compiled. `query_container` creates the scratch environments. Container management splits across different roles. A dedicated infrastructure agent handles these IDs, passing them sequentially to the testing crew for validation.

Autonomous environment configuration

`query_git` pulls the target repository into the workspace. Fetching source code happens without human triggers. The research agent analyzes the commit history and decides which test suites the execution team needs to run. `query_host` checks the underlying environment capabilities. System introspection dictates the build parameters. Your deployment agent reads this data to determine if the target architecture matches the compiled binaries before pushing to production.

Secure dependency resolution

`query_http` fetches files from URLs. Downloading external assets requires oversight. A security-focused agent monitors these downloads, ensuring the hashes match expected values before the build crew mounts them. `query_secret` creates new secrets from environment variables or files. Handling credentials demands strict isolation. The framework's moderator agent restricts access to this tool, ensuring only authorized team members can inject keys into the pipeline.

Setup guide

Set up Dagger (Programmable CI) MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Dagger (Programmable CI) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Dagger (Programmable CI) Analyst",
    goal="Access and analyze Dagger (Programmable CI) data via MCP.",
    backstory="Expert analyst with direct Dagger (Programmable CI) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Dagger (Programmable CI) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Dagger (Programmable CI) Analyst",
        goal="Access and analyze Dagger (Programmable CI) data via MCP.",
        backstory="Expert analyst with direct Dagger (Programmable CI) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Dagger (Programmable CI) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Run `pip install crewai "crewai[tools]"` in your terminal. Pass the Vinkius endpoint directly into the `mcps` array on your agent definition for the MCP server. The framework handles the connection automatically.

You control exactly which roles interact with the build engine. Import `MCPServerHTTP` from `crewai.mcp` and use `tool_filter`. This restricts destructive actions to senior agents while junior roles only read data.

The integration supports both sequential and hierarchical team structures. A manager agent can delegate container creation tasks to worker nodes. Results flow back up the chain for final deployment approval.

The Python implementation supports stdio, SSE, and Streamable HTTP. Vinkius provides a unified endpoint URL. Your team connects over HTTP without managing complex local daemon processes.

Code execution happens in a strictly isolated V8 Sandbox on Vinkius. The MCP integration processes your private Git repositories and compiled binaries. The ephemeral environment destroys all file traces immediately after the crew finishes the task.

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