How to Use the Cube.dev MCP in LlamaIndex

Q: Can LlamaIndex query Cube.dev semantic layers directly?

Yes. LlamaIndex uses loadquery to pull aggregated data directly from your Cube.dev semantic layer. The agent converts natural language questions into structured queries, bypasses raw database access, and gets clean results.

Q: How do I vector-index my Cube.dev schema using LlamaIndex?

You expose getmeta and listentities to your LlamaIndex agent. It calls these tools to retrieve your Cube.dev cubes, dimensions, and measures, then converts them into document nodes for semantic search.

Q: Does the LlamaIndex integration support Cube.dev Cloud deployments?

Yes, it does. By providing your CUBECLOUDAPIKEY, your LlamaIndex agent can call listdeployments and listenvironments to find and index the correct instance. This MCP Server lets you supply configuration parameters dynamically.

Q: How can I debug the SQL queries that LlamaIndex runs?

The LlamaIndex agent can call getsql to inspect the exact query generated by Cube.dev. This lets you debug performance or verify that LlamaIndex is asking for the correct aggregations.

Index your Cube.dev semantic schemas and query results directly into LlamaIndex vector stores for grounded RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cube.dev MCP to LlamaIndex

Create your Vinkius account to connect Cube.dev 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 Cube.dev with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index your Cube.dev metadata for smarter LlamaIndex RAG

LlamaIndex RAG systems fail when they don't understand your Cube.dev business logic. By exposing `list_entities` and `get_entity` as MCP tools, LlamaIndex can index your actual Cube.dev definitions directly into a vector store. Your LlamaIndex agent queries this local vector index to find the exact Cube.dev measures and dimensions needed for an analysis. This keeps your LlamaIndex node parser grounded in your real Cube.dev semantic definitions, preventing hallucinated metric names.

Fetch and index live Cube.dev query results

Don't let your LlamaIndex RAG agent guess the Cube.dev numbers. Your LlamaIndex agent can run `load_query` to fetch live aggregated data, then immediately feed those raw tables into LlamaIndex's document index. Your LlamaIndex agent can then synthesize natural language answers based on live, verified Cube.dev facts. If the Cube.dev query gets complex, the LlamaIndex agent uses `get_sql` to index the underlying database query for technical audits.

Monitor Cube.dev deployment readiness before indexing

Indexing stale or broken Cube.dev data ruins your LlamaIndex search index. This MCP Server lets your LlamaIndex workflow run `check_live` and `check_ready` before pulling massive Cube.dev analytical datasets. If your Cube.dev pre-aggregations are building, the LlamaIndex agent checks `get_pre_aggregation_job_status` first. It waits until the Cube.dev cache is fully built, ensuring your LlamaIndex vector store only indexes complete, high-performance data.

Setup guide

Set up Cube.dev 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 Cube.dev 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 Cube.dev tools.",
)
response = await agent.run("List recent Cube.dev 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 Cube.dev. 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 Cube.dev 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 Cube.dev MCP in LlamaIndex

Yes. LlamaIndex uses `load_query` to pull aggregated data directly from your Cube.dev semantic layer. The agent converts natural language questions into structured queries, bypasses raw database access, and gets clean results.

You expose `get_meta` and `list_entities` to your LlamaIndex agent. It calls these tools to retrieve your Cube.dev cubes, dimensions, and measures, then converts them into document nodes for semantic search.

Yes, it does. By providing your CUBE_CLOUD_API_KEY, your LlamaIndex agent can call `list_deployments` and `list_environments` to find and index the correct instance. This MCP Server lets you supply configuration parameters dynamically.

The LlamaIndex agent can call `get_sql` to inspect the exact query generated by Cube.dev. This lets you debug performance or verify that LlamaIndex is asking for the correct aggregations.

Completely. Your Cube.dev schema definitions, SQL queries, and metadata never leave your local environment. The MCP server acts as an ephemeral bridge, meaning none of your analytical data is stored or logged externally.

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