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

Q: How does Pydantic AI handle the async polling required for Dune queries?

Your agent runs a loop checking getexecutionstatus. The framework handles the async execution safely, allowing other tasks to run while waiting for the blockchain data.

Fetch type-safe blockchain data from Dune using Pydantic AI to guarantee valid SQL query results at runtime.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe SQL execution with Pydantic AI

The `execute_query` tool starts a Dune SQL run and returns an execution ID to your Pydantic AI agent. Run blockchain queries without worrying about schema drift. This setup ensures that your Python code receives exactly what it expects. If the Dune API changes its response structure, your Pydantic AI agent catches it immediately before executing further logic.

Strict state validation for pending queries

The `get_execution_status` tool tracks the progress of your active blockchain queries. Checking query progress is safer when the states are strongly typed. The server returns structured states that map directly to your Python models. This prevents your agent from attempting to read incomplete blockchain data.

Safe data extraction and query cancellation

The `get_execution_results` tool extracts the completed data rows directly into your Python environment. Pulling raw blockchain rows can corrupt agent state if the data is malformed. If a query runs too long, call `cancel_execution` to terminate it. The framework ensures the MCP server's cancellation confirmation matches your strict schema requirements.

Setup guide

Set up Dune Analytics (Web3 SQL Analytics API) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "dune-analytics-web3-sql-analytics-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Dune Analytics (Web3 SQL Analytics API) tools.",
)

result = await agent.run("List recent Dune Analytics (Web3 SQL Analytics API) transactions")
print(result.output)

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 Pydantic AI

Use the MCP server toolset class with your Vinkius server URL. Pass this toolset into your Pydantic AI Agent constructor to expose the SQL tools to your model.

The framework will raise a validation error at runtime. This prevents your Pydantic AI agent from processing corrupted blockchain data or hallucinating missing fields.

Yes. Because Pydantic AI is model-agnostic, you can use these Dune tools with OpenAI, Anthropic, or local models running on your own hardware.

Your agent runs a loop checking `get_execution_status`. The framework handles the async execution safely, allowing other tasks to run while waiting for the blockchain data.

Everything runs inside secure, ephemeral V8 isolates on the Vinkius MCP host. Your API keys and raw SQL data rows are processed in-memory and never cached or stored on Vinkius servers.

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