Tinybird Data Platform MCP. Audit, query, and manage real-time data flows in chat.
Tinybird Data Platform connects your AI agent directly to a real-time data warehouse, giving you hands-on control over complex analytics infrastructure. You can manage all your data sources and transformation logic from chat alone. Use this MCP to list every available workspace, check row counts for any data source, audit pipeline status, or run arbitrary SQL queries against live data. It's full operational oversight for data engineers.
Give Claude and any AI agent real-world access
List every data source and workspace available in your current analytical environment.
Get detailed information, including row counts and storage sizes, for any specified data source.
List all transformation pipelines (Pipes) or retrieve the specific SQL logic used within them.
Execute any arbitrary SQL query against your live data warehouse using ClickHouse dialect.
Run a specific Pipe and immediately retrieve the results as structured JSON output.
Ask an AI about this
Waiting for input…
What AI agents can do with Tinybird Data Platform with 10 Tools
Use these tools to manage everything from listing workspaces to executing complex real-time SQL queries against your entire data platform.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Tinybird Data Platform MCPExecute Sql Query
Runs an arbitrary SQL query directly against the Tinybird workspace data.
Get Datasource Details
Retrieves detailed information about a specific Data Source in the platform.
Get Pipe Details
Gets comprehensive details for any specified data transformation Pipe.
Get Datasource Stats
Pulls current ingestion and usage statistics for a selected Data Source.
List Datasources
Retrieves a full list of every data source connected to the workspace.
List Pipe Nodes
Lists all individual SQL nodes contained within a specific transformation Pipe.
List Pipes
Retrieves a list of every available data transformation pipe in the workspace.
List Auth Tokens
Lists all authentication tokens, allowing you to audit access control within the...
List Workspaces
Retrieves a list of every available data workspace across your account.
Query Pipe Data
Executes an entire Pipe and returns the resulting dataset as structured JSON.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on each call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Tinybird Data Platform, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,200+ others, all in one place
- Add new capabilities to your AI anytime you want
- Connections are secured and governed automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog weekly
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Tinybird. 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.
VINKIUS CLOUD
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on each call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
The Pain of Context-Switching Data Checks
Today, checking the health of your analytics platform is a multi-step chore. You open the main dashboard to check Data Source A's row count. Then you tab over to the Pipelines section to see if Pipe B has run recently, and finally, you might have to copy a token ID into a separate terminal window just to audit the permissions. It's clicking, switching tabs, and constantly copying credentials.
With this MCP, all that operational visibility lives inside your chat window. You simply ask your agent to get_datasource_stats for Source A while simultaneously listing_pipes to check Pipe B's status. The agent gathers all that disparate information and presents it back in one clean, conversational response.
Tinybird Data Platform MCP: Querying Live Insights
Gone are the days of manually running a query in a separate client just to validate if the data is ready. You can now use execute_sql_query and then immediately follow up with query_pipe_data on the resulting dataset, all within the same chat session.
The result is a continuous flow of information, making your entire analytical workflow feel less like software operations and more like having an expert teammate sitting right next to you.
What Tinybird Data Platform MCP does for your AI
This MCP lets you treat your entire analytical infrastructure like a conversational service. Instead of opening the Tinybird dashboard and clicking through five different tabs just to check if a data stream is healthy, your agent handles it all. You can ask it to list every workspace available or inspect a specific Data Source's current ingestion stats—all in natural language.
It lets you run complex SQL queries without writing boilerplate connection code yourself. Furthermore, the platform allows deep dives into how your data changes, enabling you to retrieve the exact SQL logic used by any Pipe and even execute those published transformations for instant results. Connecting this MCP through Vinkius means you get centralized control over all these critical functions from one place, making operational monitoring feel like a simple chat conversation.
019d848e-f293-7286-96e3-4cf81e16a375 How to set up Tinybird Data Platform MCP
The bottom line is you manage complex data flows using simple conversation prompts.
Subscribe to this MCP on Vinkius and provide your Tinybird Admin Token.
Ask your agent to perform an action, such as listing all available data sources or checking the stats for a specific Data Source.
The agent executes the necessary command, pulls the real-time metrics, and presents the results directly in chat.
Who uses Tinybird Data Platform MCP
Data Engineers and Analytics Leads need this. They're tired of context-switching between the dashboard, SQL IDEs, and monitoring tools just to validate a single query or audit a failing pipeline. This MCP puts full operational visibility into your chat window.
Audits pipe logic using list_pipe_nodes to understand transformation dependencies, and runs execute_sql_query for quick validation during development.
Checks data source stats using get_datasource_stats or executes a query_pipe_data command without having to navigate the entire analytics platform.
Monitors ingestion performance and token scopes by calling list_auth_tokens, ensuring all pipelines are running within scope.
Benefits of connecting Tinybird Data Platform MCP
Stop guessing if your data is fresh. Use get_datasource_stats to immediately check row counts and ingestion usage for any source without opening a dashboard tab.
Debugging complex pipelines just got easier. You can use list_pipe_nodes or get_pipe_details to see the exact SQL logic used in any transformation, accelerating development time.
Run queries instantly. Use execute_sql_query to fire off ad-hoc analytical requests and explore your data directly via natural language command.
Full infrastructure visibility. Need to know what workspaces exist? list_workspaces gives you a quick inventory of everything connected.
Test transformations safely. Instead of running an entire Pipe in the GUI, use query_pipe_data to execute it and get the structured JSON output immediately.
Tinybird Data Platform MCP use cases
Checking data health on a Friday afternoon
A product analyst needs to know if the user event stream has been updated since last night's deployment. Instead of clicking into the 'user_events' source and scrolling through metrics, they just ask their agent to get_datasource_stats. The agent instantly replies with the latest row count and ingestion status.
Debugging a broken data pipeline
A data engineer finds that the 'monthly_report' pipe is failing intermittently. They use list_pipe_nodes to see if the SQL logic changed, then run get_datasource_details on the upstream source to verify field types, pinpointing the failure point immediately.
Quickly proving a hypothesis
A manager wants to know how many users came from 'partner X' last month. Instead of building a new dashboard and waiting for approval, they run an execute_sql_query command directly through the agent, getting the answer in seconds.
Auditing security access
The DevOps team needs to verify which services have access to sensitive data. They use list_auth_tokens to generate a full audit trail of all active tokens and check their scopes, ensuring least privilege is maintained.
Tinybird Data Platform MCP tradeoffs
What to watch out for, and the recommended way to handle each one.
Treating the MCP like an API wrapper
Sending repetitive commands like 'List Data Sources. Now get stats for Data Source A. Then list Pipes.' This requires multiple steps and context switching.
Ask your agent to consolidate: 'Give me a full audit of data sources, including their current row counts and listing all associated pipes in the workspace.' The MCP handles the sequence.
Over-engineering simple queries
Wasting time creating complex views or new dedicated dashboards just for one simple metric.
Use execute_sql_query. If you need a quick number, run it directly with the agent instead of building permanent infrastructure.
Assuming data completeness
Running query_pipe_data and assuming the result set is perfect without checking the source.
Always preface pipe execution by calling get_datasource_stats first. This verifies that the underlying Data Source has sufficient, up-to-date metrics.
When to use Tinybird Data Platform MCP
Use this MCP if your core problem is accessing and managing real-time data infrastructure through chat conversation. If you need to run ad-hoc queries (execute_sql_query) or audit the state of multiple connected services (list_datasources, list_auth_tokens), this is built for you. Don't use it if your only goal is basic file storage management; that requires a different type of integration. Similarly, don't rely on it to fix bad data quality—it only reports what the data is. If you just need to build an entirely new reporting layer from scratch without querying existing sources, look for ETL tools rather than this MCP.
Frequently asked questions about Tinybird Data Platform MCP
How does Tinybird Data Platform MCP list all data sources? +
You use the list_datasources tool. It immediately provides a comprehensive inventory of every source connected to your workspace, giving you an at-a-glance view of what's available for analysis.
Can I check my data pipeline status using Tinybird Data Platform MCP? +
Yes. You can use list_pipes to see every defined pipe, and then get_pipe_details or query_pipe_data to understand its logic or execute it for results.
What is the difference between execute_sql_query and query_pipe_data? +
execute_sql_query runs any SQL you write, giving maximum flexibility. query_pipe_data executes a pre-built Pipe, ensuring that your logic follows established data transformation rules.
Does Tinybird Data Platform MCP help with security audits? +
Absolutely. You can use list_auth_tokens to retrieve a full list of all authentication tokens and audit who has access across the workspace.