How to Use the Northflank (Developer Cloud & Orchestration) MCP in LangChain

Q: How can I use LangChain to create a new Northflank project and deploy a service?

Your LangChain agent can call createproject to make the new space. This MCP server then lets it use the outputted project ID to call triggerbuild for the correct service, completing the deployment chain.

Q: What's the best way to handle secrets with Northflank (Developer Cloud & Orchestration) and LangChain?

Use listsecrets within a ReAct agent. The agent can fetch available secret groups and then decide which ones to apply when creating new jobs or services, ensuring you don't expose sensitive data accidentally.

Q: Does this MCP server let me delete projects?

Absolutely. The deleteproject tool is included, allowing your agent to perform cleanup tasks. It's powerful, so you'll want to add confirmation steps to your chains to prevent accidental deletions.

Build autonomous DevOps agents for Northflank with LangChain. Chain commands to create, deploy, and manage your cloud infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northflank (Developer Cloud & Orchestration) MCP to LangChain

Create your Vinkius account to connect Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Deployments with Reasoning Chains

Your agent can build a complete deployment pipeline on its own. It starts by running `list_projects` to find the right environment, then uses `trigger_build` to kick off a new deployment for a specific service. If the build fails, the agent can reason about what went wrong. It might check the service status with `get_service` or decide to `restart_service` if it suspects a memory leak, all without human intervention.

Manage Infrastructure with your LangChain MCP Server

Give your agent the keys to your Northflank account. It can spin up entire preview environments by chaining `create_project` with `list_secrets` to ensure the right configuration is applied. When the pull request is merged, the same agent can run `delete_project` to tear everything down. This isn't just a script; it's a dynamic chain of actions based on real-time events.

Perform Complex Infrastructure Audits

Build an agent that audits your infrastructure for compliance. It can iterate through every project using `list_projects`, then inspect each one with `get_project` to check resource limits. The agent can then dive deeper, using `list_services` and `list_jobs` to map out all running processes and scheduled tasks. You get a full report, generated by a logical chain of API calls, not a static script.

Setup guide

Set up Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) 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({
    "northflank-developer-cloud-orchestration-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 Northflank (Developer Cloud & Orchestration) 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 Northflank. 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 Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) MCP in LangChain

Your LangChain agent can call `create_project` to make the new space. This MCP server then lets it use the outputted project ID to call `trigger_build` for the correct service, completing the deployment chain.

Use `list_secrets` within a ReAct agent. The agent can fetch available secret groups and then decide which ones to apply when creating new jobs or services, ensuring you don't expose sensitive data accidentally.

Yes. You can create a chain that monitors logs or alerts. When a failure is detected, the agent can call `get_service` to confirm the state and then execute `restart_service` to bring it back online.

Absolutely. The `delete_project` tool is included, allowing your agent to perform cleanup tasks. It's powerful, so you'll want to add confirmation steps to your chains to prevent accidental deletions.

Your MCP Server only processes the data needed for each tool call, like project IDs, service names, and secret group metadata. All connections are over HTTPS, and Vinkius isolates each request in an ephemeral sandbox. Your Northflank credentials are never exposed to the agent.

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