How to Use the Dune Analytics (Web3 SQL Analytics API) MCP in LlamaIndex

Q: How do I index query results using Dune Analytics (Web3 SQL Analytics API) and LlamaIndex?

Start the query with executequery to get an execution ID. Poll getexecutionstatus until it finishes, then fetch the rows with getexecutionresults to convert them into indexable document nodes.

Q: Can LlamaIndex automatically stop a slow database query?

Yes, your agent can call cancelexecution if a query takes too long to complete. This is useful when the agent decides the user's question no longer requires that specific dataset.

Q: How are the SQL results formatted for my index?

The getexecutionresults tool returns JSON-formatted rows. LlamaIndex reads these rows as structured key-value pairs, making it easy to create metadata-rich text chunks for your vector database.

Index raw blockchain SQL results directly into LlamaIndex vector stores for ground-truth Web3 query answering.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dune Analytics (Web3 SQL Analytics API) MCP to LlamaIndex

Create your Vinkius account to connect Dune Analytics (Web3 SQL Analytics API) 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 Dune Analytics (Web3 SQL Analytics API) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live Web3 data into your LlamaIndex RAG pipeline

The `execute_query` tool fetches raw blockchain data to build a dynamic knowledge base for your agent. Instead of relying on static documents, your index pulls fresh on-chain data directly from Dune's tables. Once `get_execution_status` confirms the run is complete, the agent loads the raw rows using `get_execution_results`. These rows are converted into document nodes, parsed, and indexed for immediate semantic search.

Avoid hallucinations with verifiable SQL ground truth

Your agent uses `execute_query` via this MCP Server to run specific analytical queries when a user asks about token volumes or smart contract activity. This ensures the engine answers using actual database records rather than guessing. If a query runs too long or becomes redundant, the agent calls `cancel_execution` to free up resources. This direct database access keeps your agent's answers grounded in real-time on-chain metrics.

Track query status before indexing

The `get_execution_status` tool prevents your indexing pipeline from loading incomplete or corrupted data. Your ingestion script polls this endpoint to verify that the SQL engine has finished processing the blockchain logs. This check keeps your vector store clean. By only calling `get_execution_results` on completed runs, you avoid indexing partial tables or error messages into your semantic database.

Setup guide

Set up Dune Analytics (Web3 SQL Analytics API) 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 Dune Analytics (Web3 SQL Analytics API) 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 Dune Analytics (Web3 SQL Analytics API) tools.",
)
response = await agent.run("List recent Dune Analytics (Web3 SQL Analytics API) 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 Dune Analytics. 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 Dune Analytics (Web3 SQL Analytics API) 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 Dune Analytics (Web3 SQL Analytics API) MCP in LlamaIndex

Start the query with `execute_query` to get an execution ID. Poll `get_execution_status` until it finishes, then fetch the rows with `get_execution_results` to convert them into indexable document nodes.

Yes, your agent can call `cancel_execution` if a query takes too long to complete. This is useful when the agent decides the user's question no longer requires that specific dataset.

This connector handles the protocol translation natively, allowing your LlamaIndex agent to call the tools directly without custom API integration code. It runs in a secure, sandboxed environment on Vinkius.

The `get_execution_results` tool returns JSON-formatted rows. LlamaIndex reads these rows as structured key-value pairs, making it easy to create metadata-rich text chunks for your vector database.

Your query parameters and returned datasets stay within an isolated V8 sandbox on Vinkius. This MCP Server processes data in memory during the execution lifecycle and is destroyed immediately after your client disconnects.

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