How to Use the Northbeam MCP in LangChain

Q: How do I use Northbeam and LangChain to create a data export?

Your LangChain agent calls createdataexport with the metrics and breakdowns you need. The tool returns an export ID, which you then use with getexportstatus in the next step of your chain.

Q: Can I see all available metrics from Northbeam in my LangChain app?

Yes. Have your agent call listmetrics. It returns a clean list of everything you can include in an export, like 'Attributed Revenue' and 'Spend'.

Q: How can I check if a Northbeam export is finished using my agent?

The getexportstatus tool is what you need. Your agent just passes the export ID to it. You can put this in a loop until the status changes to 'completed'.

Build attribution analysis chains for LangChain that automatically export and check Northbeam reports.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northbeam MCP to LangChain

Create your Vinkius account to connect Northbeam 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 Northbeam with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Custom Attribution Workflows

Start a chain that finds the right attribution model. Your agent can call `list_attribution_models` and `list_breakdowns` to see what's available, then decide which combination to use for an export. Once the parameters are set, the next link in the chain is `create_data_export`. The agent gets the export ID back and passes it to the next tool. It's a simple, observable sequence you can trace in LangSmith.

Create Self-Correcting Data Pipelines

This toolset lets your LangChain agent poll for results. After calling `create_data_export`, your agent can loop on `get_export_status` until the report is ready. No more manual checking. When the status hits 'completed', the agent knows it can move on. You can build logic to list recent files with `list_recent_exports` or trigger a webhook via another service. The whole process is visible.

Audit Northbeam Settings with LangChain

Your agent can use `get_account_info` and `get_dashboard_settings` to check your current Northbeam configuration. It's a good way to programmatically verify that your workspace is set up correctly before running exports. Chain this with other tools. For example, have an agent check the settings, then compare them against a list of approved models from `list_attribution_models`. If there's a mismatch, it flags it for review. This MCP Server makes your agent the auditor.

Setup guide

Set up Northbeam 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 Northbeam 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({
    "northbeam-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 Northbeam 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 Northbeam. 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 Northbeam 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 Northbeam MCP in LangChain

Your LangChain agent calls `create_data_export` with the metrics and breakdowns you need. The tool returns an export ID, which you then use with `get_export_status` in the next step of your chain.

Yes. Have your agent call `list_metrics`. It returns a clean list of everything you can include in an export, like 'Attributed Revenue' and 'Spend'.

Use a client that can handle multiple tools and pass the list from this MCP server to your agent. This lets the agent decide the sequence, like calling `list_attribution_models` first, then `create_data_export`.

The `get_export_status` tool is what you need. Your agent just passes the export ID to it. You can put this in a loop until the status changes to 'completed'.

Yes. Your connection is protected by your Vinkius endpoint token. The server only handles your Northbeam attribution metrics, like revenue and spend data, and it all happens within Vinkius's ephemeral, zero-trust sandbox.

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