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

Q: How do multiple AutoGen agents coordinate a query using Dune Analytics (Web3 SQL Analytics API)?

One agent initiates the query with executequery and shares the execution ID. Another agent polls getexecutionstatus and triggers getexecutionresults once the data is ready for the group to analyze.

Q: What happens if a query fails in the middle of an agent conversation?

The getexecutionstatus tool will return a failed state. Your analyst agent can read this error message, adjust the SQL syntax, and call executequery again to retry.

Let your AutoGen agents debate, execute, and verify complex blockchain SQL queries in AutoGen multi-agent workflows.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive multi-agent consensus with this MCP Server

The `execute_query` tool lets your data-analyst agent pull live blockchain tables while other agents wait for the results. One agent writes the SQL, triggers the execution, and shares the execution ID with the group. A separate verification agent monitors the query using `get_execution_status`. Once completed, it fetches the rows using `get_execution_results` and passes them to a critic agent to verify the financial logic.

Manage query budgets via collaborative cancellation

A budget-monitoring agent can invoke `cancel_execution` if a query runs too long or exceeds credit limits. This MCP Server setup prevents autonomous loops from burning through your Dune API credits on accidental infinite queries. The decision to cancel is handled entirely through agent conversation. If the status checking tool shows a query is stuck, the manager agent commands the executor to stop the run immediately.

Verify data state before agent decisions

The `get_execution_status` tool ensures your agents never argue over incomplete data. The analyst agent must confirm a successful run status before presenting the final dataset to the rest of the group. This protocol prevents agents from making decisions based on empty tables or partial runs. It creates a reliable checkpoint in your multi-step autonomous workflows.

Setup guide

Set up Dune Analytics (Web3 SQL Analytics API) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Dune Analytics (Web3 SQL Analytics API) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Dune Analytics (Web3 SQL Analytics API)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Dune Analytics (Web3 SQL Analytics API) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Dune Analytics (Web3 SQL Analytics API)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Dune Analytics (Web3 SQL Analytics API) data")
    print(result.messages[-1].content)

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 AutoGen

One agent initiates the query with `execute_query` and shares the execution ID. Another agent polls `get_execution_status` and triggers `get_execution_results` once the data is ready for the group to analyze.

Yes, any agent in the group with access to the execution ID can call `cancel_execution`. This allows your supervisor agent to stop runaway queries if they exceed your set budget.

Vinkius manages the Dune API keys securely on their platform. Your AutoGen setup only needs a single endpoint token to connect, removing the need to distribute API keys across multiple local agents.

The `get_execution_status` tool will return a failed state. Your analyst agent can read this error message, adjust the SQL syntax, and call `execute_query` again to retry.

All data passing through this MCP Server is processed in ephemeral memory within a zero-trust V8 sandbox. No query text or blockchain execution results are cached or stored on Vinkius servers after the session ends.

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