How to Use the Databox MCP in LlamaIndex

Q: How do I connect Databox to my LlamaIndex RAG app?

You'll use the McpToolSpec after installing the LlamaIndex tools for MCP. This spec wraps the Databox tools, like getdatasetdetails, making them available to your FunctionAgent.

Q: Can LlamaIndex query the actual data inside a Databox dataset?

Not the raw time-series data points. LlamaIndex can call listdatasetmetrics to get the names and types of metrics, and it can index that metadata. It uses pushmetricsdata to add data, not read it back.

Q: How does indexing work with Databox and LlamaIndex?

When your agent calls a tool like listdatasets, LlamaIndex takes the JSON response and converts it into text chunks. These chunks are then embedded and stored in a vector database, making the content of that API call searchable.

Q: Can I filter which Databox tools my LlamaIndex agent can use?

Yes, the McpToolSpec supports an allowedtools filter. You can give an agent access only to read-only tools like listdatasets and getcurrentuser, preventing it from making changes.

Build a knowledge base from your live Databox metrics with LlamaIndex. Ask questions, get answers grounded in your data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databox MCP to LlamaIndex

Create your Vinkius account to connect Databox 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 Databox with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn API calls into searchable knowledge

This is where LlamaIndex shines. Your agent calls a Databox tool like `list_dataset_metrics` or `get_storage_statistics`. LlamaIndex doesn't just return the data; it automatically indexes it into a vector store. Now you can ask natural language questions about your metrics. Instead of writing a script to parse API output, you just ask, "What were the key metrics for the Q3 campaign dataset?" LlamaIndex finds the answer from its indexed knowledge.

Your Databox MCP Server as a knowledge source

Use LlamaIndex to build a RAG pipeline that understands your Databox setup. Your agent can periodically run `list_data_sources` and `list_datasets`, indexing the configuration. This lets you query your own infrastructure. Ask your agent, "Which datasets are connected to our production data source?" It will retrieve the answer from the vector index, giving you grounded information without another live API call.

Combine indexing with action

A LlamaIndex agent can do more than just answer questions. It can reason over its knowledge base to take action. For example, it can query its index for unused datasets, then confirm with `list_activity_logs`. Once it identifies a candidate for cleanup, it can use the `delete_dataset` tool. This combines the retrieval power of RAG with the ability to perform operations, all within the same agent.

Setup guide

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

You'll use the `McpToolSpec` after installing the LlamaIndex tools for MCP. This spec wraps the Databox tools, like `get_dataset_details`, making them available to your `FunctionAgent`.

Not the raw time-series data points. LlamaIndex can call `list_dataset_metrics` to get the names and types of metrics, and it can index that metadata. It uses `push_metrics_data` to add data, not read it back.

When your agent calls a tool like `list_datasets`, LlamaIndex takes the JSON response and converts it into text chunks. These chunks are then embedded and stored in a vector database, making the content of that API call searchable.

Yes, the `McpToolSpec` supports an `allowed_tools` filter. You can give an agent access only to read-only tools like `list_datasets` and `get_current_user`, preventing it from making changes.

Yes. Your connection to the MCP Server is authenticated with a single Vinkius endpoint token. LlamaIndex uses this token for all API calls, so your actual Databox credentials are never exposed to the agent or stored in your code.

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