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

Chain your pipeline logic directly into LangChain agents with the Dagger (Programmable CI) MCP Server.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run GraphQL queries from LangChain

Feed Dagger engine operations directly into your LangChain chains. You use `execute_graphql_query` to build directed acyclic graphs of your build steps, passing results between nodes as inputs. This keeps your pipeline logic inside your agent's reasoning loop. You stop writing static YAML and start building dynamic, code-driven workflows.

Manage build secrets in LangChain

Handle sensitive data by calling `query_secret` within your agent's execution chain. It supports environment variables, file paths, and local commands to inject credentials securely. Your agent decides when to pull these secrets during the build lifecycle. LangSmith tracks every call, so you see exactly how and when your keys get used.

Control containers via LangChain

Create and track ephemeral build environments using `query_container`. Your agent spawns scratch containers, runs your logic, and discards the state afterward. You avoid polluting your host machine by offloading all filesystem tasks to Dagger. It acts as the backbone for your agent's physical build actions.

Setup guide

Set up Dagger (Programmable CI) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Dagger (Programmable CI) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "dagger-programmable-ci-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Dagger (Programmable CI) transactions"
    })
    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 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 LangChain

You use LangSmith to monitor the MCP tool outputs. Since every call is a link in your chain, the platform logs the latency and the exact JSON payload returned by the engine.

Yes, you pass the tool list into your LangGraph constructor. Different agents in your team can invoke specific build tools based on their assigned role in the chain.

It depends on your setup. You can use a stateless transport, or initialize a persistent session through the client to maintain context across complex build steps.

You write raw GraphQL queries and execute them via the server. The agent constructs these queries dynamically based on the goals you define in your prompt.

Variables exist only within the memory of the Dagger engine process. We do not persist your secrets in any database or logs, ensuring your build environment stays clean.

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