Where do I find my Tinybird Admin Token?

Log in to your [**Tinybird Dashboard**](https://app.tinybird.co/), select a workspace, and go to the 'Auth Tokens' section. You can use the Admin Token or create a custom one with the necessary scopes.

Which SQL dialect does Tinybird use?

Tinybird is powered by ClickHouse, so it uses the ClickHouse SQL dialect, which includes powerful functions for high-performance analytical processing.

Tinybird Data Platform MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Tinybird Data Platform
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Tinybird Data Platform through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Tinybird Data Platform "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Tinybird Data Platform?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Tinybird Data Platform MCP Server

Connect your AI agent to Tinybird, the real-time data platform for developers. This integration allows you to oversee your analytical infrastructure, manage ingestion storage (Data Sources), and interact with transformation logic (Pipes) through natural conversation.

Pydantic AI validates every Tinybird Data Platform tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Infrastructure Oversight — List and inspect all your Data Sources and Pipes in real-time
Transformation Analysis — Retrieve SQL logic and nodes for any Pipe to understand how data is being processed
Live Querying — Execute published Pipes or run arbitrary SQL queries (ClickHouse dialect) to explore your data directly via the agent
Operational Metrics — Check ingestion stats, row counts, and storage sizes for your analytical units
Access Control — List and audit authentication tokens and workspace configurations

The Tinybird Data Platform MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Tinybird Data Platform to Pydantic AI via MCP

Follow these steps to integrate the Tinybird Data Platform MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Tinybird Data Platform with type-safe schemas

Why Use Pydantic AI with the Tinybird Data Platform MCP Server

Pydantic AI provides unique advantages when paired with Tinybird Data Platform through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Tinybird Data Platform integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Tinybird Data Platform connection logic from agent behavior for testable, maintainable code

Tinybird Data Platform + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Tinybird Data Platform MCP Server delivers measurable value.

Type-safe data pipelines: query Tinybird Data Platform with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Tinybird Data Platform tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Tinybird Data Platform and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Tinybird Data Platform responses and write comprehensive agent tests

Tinybird Data Platform MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Tinybird Data Platform to Pydantic AI via MCP:

execute_sql_query

Execute an arbitrary SQL query against the Tinybird workspace

get_datasource_details

Get comprehensive information for a specific Data Source

get_datasource_stats

Retrieve ingestion and usage statistics for a Data Source

get_pipe_details

Get detailed information for a specific Pipe

list_auth_tokens

Retrieve a list of all authentication tokens in the workspace

list_datasources

Retrieve a list of all Data Sources in the current workspace

list_pipe_nodes

List all SQL nodes within a specific Pipe

list_pipes

Retrieve a list of all Pipes in the current workspace

list_workspaces

Retrieve a list of available workspaces

query_pipe_data

Execute a Pipe and retrieve the results as JSON

Example Prompts for Tinybird Data Platform in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Tinybird Data Platform immediately.

"List all data sources in my Tinybird workspace."

"Run the pipe 'monthly_revenue_summary' with limit 5."

Troubleshooting Tinybird Data Platform MCP Server with Pydantic AI

Common issues when connecting Tinybird Data Platform to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Tinybird Data Platform + Pydantic AI FAQ

Common questions about integrating Tinybird Data Platform MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Tinybird Data Platform MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.