How to Use the Dune Analytics (Web3 SQL Analytics API) MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK handle query timeouts with this Dune Analytics (Web3 SQL Analytics API) toolset?

Yes. Your agent can monitor progress and call cancelexecution if a query takes too long. This prevents your OpenAI Agents SDK from burning API credits on stuck blockchain queries.

Q: How do I handle large datasets returned by the Dune tools?

Your agent should poll with getexecutionstatus first. Once finished, use the MCP server to fetch the rows in manageable chunks to avoid hitting context limits.

Run SQL on blockchain data directly from your OpenAI Agents SDK pipelines with managed execution tracking.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dune Analytics (Web3 SQL Analytics API) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute raw Web3 SQL queries via OpenAI Agents SDK

The `execute_query` tool lets your Python agent trigger SQL queries against Dune's blockchain database. By calling this, the agent kicks off the run on Dune's compute cluster and gets an execution ID. The SDK handles the handoff between specialized agents. One agent can spawn the query while another monitors the run, ensuring your pipeline does not block while waiting for heavy chain data to compile.

Asynchronous status checks with built-in guardrails

The `get_execution_status` tool checks whether your active blockchain query is still running or completed. Heavy blockchain queries take time to resolve, so polling prevents your agent from freezing. This MCP server integrates with OpenAI's validation layer. The SDK verifies the agent's intent before polling, keeping your execution loop safe from runaway API costs.

Retrieve data rows and manage active executions

The `get_execution_results` tool pulls the raw data rows into your agent's context window once a query finishes. This lets the agent analyze token volumes, gas fees, or smart contract interactions immediately. If a query runs too long, the agent triggers `cancel_execution` to kill the job. This keeps your Dune API budget in check during complex autonomous multi-agent runs.

Setup guide

Set up Dune Analytics (Web3 SQL Analytics API) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dune Analytics (Web3 SQL Analytics API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dune Analytics (Web3 SQL Analytics API) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dune Analytics (Web3 SQL Analytics API) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dune Analytics (Web3 SQL Analytics API) Agent",
            instructions="You have access to Dune Analytics (Web3 SQL Analytics API) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the OpenAI agent package and configure the server URL in your python script. Pass the Dune MCP server connection to your agent constructor to let it auto-discover the SQL execution tools.

Yes. Your agent can monitor progress and call `cancel_execution` if a query takes too long. This prevents your OpenAI Agents SDK from burning API credits on stuck blockchain queries.

No. The tools are auto-discovered by the OpenAI Agents SDK using the MCP standard. The agent automatically knows how to structure the parameters for `execute_query` based on the exposed schema.

Your agent should poll with `get_execution_status` first. Once finished, use the MCP server to fetch the rows in manageable chunks to avoid hitting context limits.

Vinkius runs the server in an isolated V8 sandbox. Your Dune API keys and SQL query results are never stored on disk, keeping your proprietary blockchain metrics completely private.

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