How to Use the Northbeam MCP in LlamaIndex

Q: How can I use LlamaIndex to search my past Northbeam exports?

Have your agent call listrecentexports and index the results. Now you can perform semantic searches over your export history, asking questions like "find exports that included campaign breakdowns."

Q: Can LlamaIndex remember which Northbeam attribution models I prefer?

Yes. Call listattributionmodels and index the output. Your agent now has a knowledge base of your available models, making its future suggestions about exports much more relevant.

Q: What's the process for connecting the Northbeam MCP server to LlamaIndex?

Use the McpToolSpec after creating a basic client. This exposes the Northbeam tools so you can pass them to your FunctionAgent. LlamaIndex will then be able to call the tools and index their output.

Q: How do I check my account settings for Northbeam using a LlamaIndex agent?

Use the getaccountinfo tool. Your agent can call it and index the metadata. This grounds your agent, so it knows the specifics of your account configuration.

Index Northbeam attribution data with LlamaIndex to ground your agent's answers in real performance metrics.

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 LlamaIndex

Create your Vinkius account to connect Northbeam to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Attribution Data into Knowledge

Use `list_metrics`, `list_breakdowns`, and `list_attribution_models` to fetch your account's reporting structure. LlamaIndex doesn't just see this data once; it indexes the output into a vector store. Now your agent can answer questions about your setup without hitting the API again. Ask "what breakdowns are available for Clicks Only model?" and it will pull the answer from its indexed knowledge, grounded in the last `list_breakdowns` call.

Index Your Export History

Your agent can call `create_data_export` to start a report. More importantly, it can then poll `get_export_status` and, once complete, index the result along with the initial parameters. Over time, you build a searchable history of every report you've run. You can ask your LlamaIndex agent, "show me all ROAS reports from last week" and it will query its index of past `create_data_export` calls and their final statuses.

Your LlamaIndex Agent Knows Your Setup

This MCP Server gives your RAG application a direct line to your Northbeam reality. The `get_account_info` and `get_dashboard_settings` tools provide hard data about your workspace. When LlamaIndex ingests this, your agent's responses get more accurate. It won't hallucinate settings or models because its knowledge base is built from actual API responses, not just general training data.

Setup guide

Set up Northbeam MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Northbeam MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Northbeam tools.",
)
response = await agent.run("List recent Northbeam data")

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 LlamaIndex

Have your agent call `list_recent_exports` and index the results. Now you can perform semantic searches over your export history, asking questions like "find exports that included campaign breakdowns."

Yes. Call `list_attribution_models` and index the output. Your agent now has a knowledge base of your available models, making its future suggestions about exports much more relevant.

Use the `McpToolSpec` after creating a basic client. This exposes the Northbeam tools so you can pass them to your FunctionAgent. LlamaIndex will then be able to call the tools and index their output.

Use the `get_account_info` tool. Your agent can call it and index the metadata. This grounds your agent, so it knows the specifics of your account configuration.

Your Vinkius token secures the connection. The server, running in a sandboxed environment, only processes your Northbeam marketing data (like transactions and ad spend) for your agent to index. Data isn't persisted on the server itself.

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