How to Use the Octoboard MCP in LlamaIndex

Q: What happens if Octoboard has a connection error?

The getapistatus tool lets your agent check the link health. If it's down, your index won't attempt to pull stale or broken data.

Q: Is it easy to filter specific clients in LlamaIndex?

Use listagencyclients to get a list of your accounts. You can then restrict your agent to only index data for specific client IDs.

Turn marketing performance data into a searchable knowledge base using LlamaIndex and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Octoboard MCP to LlamaIndex

Create your Vinkius account to connect Octoboard to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Octoboard with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index your marketing metrics with LlamaIndex

Stop treating report data as static numbers. Use this MCP Server to pull your latest stats via `push_text_metric` and have LlamaIndex ingest them into your vector store. Your RAG application now knows the actual performance of your campaigns. You can query your own history to explain why numbers changed last month.

Ground your AI in real Octoboard data

Use `list_automated_reports` to grab existing report structures and feed them into your index. This gives your agent the context it needs to generate accurate, data-backed insights. No more guessing based on training data. Your agent answers questions using the live numbers it pulls from your agency accounts.

Verify your Octoboard credentials securely

Run `test_octoboard_auth` to make sure your agent has the right access before it starts building your index. It’s a simple check that saves you from debugging empty data sets later. Once the connection is confirmed, your agent can reliably reach into your dashboard data to answer client questions.

Setup guide

Set up Octoboard 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 Octoboard 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 Octoboard tools.",
)
response = await agent.run("List recent Octoboard 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 Octoboard. 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.