# Tinybird Data Platform MCP > 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. ## Overview - **Category:** loved-by-devs - **Price:** Free - **Tags:** real-time-data, data-ingestion, sql-queries, data-pipelines, api-endpoints, analytics-infrastructure ## Description 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. ## Tools ### execute_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 workspace. ### 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. ## Prompt Examples **Prompt:** ``` List all data sources in my Tinybird workspace. ``` **Response:** ``` Fetching data sources... I found 3 sources: 'events_log' (1.2M rows), 'users_data' (50k rows), and 'api_analytics' (800k rows). Which one would you like to inspect? ``` **Prompt:** ``` Run the pipe 'monthly_revenue_summary' with limit 5. ``` **Response:** ``` Executing pipe... Here are the top 5 records from 'monthly_revenue_summary': 1. Jan ($12k), 2. Feb ($15k), 3. Mar ($11k)... ``` ## Capabilities ### Inventory Data Sources List every data source and workspace available in your current analytical environment. ### Audit Data Source Status Get detailed information, including row counts and storage sizes, for any specified data source. ### Examine Data Pipelines List all transformation pipelines (Pipes) or retrieve the specific SQL logic used within them. ### Run Ad-Hoc Queries Execute any arbitrary SQL query against your live data warehouse using ClickHouse dialect. ### Analyze Pipeline Execution Run a specific Pipe and immediately retrieve the results as structured JSON output. ## 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. ## Benefits - 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. ## How It Works The bottom line is you manage complex data flows using simple conversation prompts. 1. Subscribe to this MCP on Vinkius and provide your Tinybird Admin Token. 2. Ask your agent to perform an action, such as listing all available data sources or checking the stats for a specific Data Source. 3. The agent executes the necessary command, pulls the real-time metrics, and presents the results directly in chat. ## Frequently Asked Questions **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.