Tinybird MCP Server

What does “Tinybird” MCP Server do?

The Tinybird MCP (Model Context Protocol) Server is designed to connect AI assistants with the Tinybird data analytics platform. It enables seamless interaction between AI clients and Tinybird workspaces, making it possible to query data sources, retrieve results from API endpoints, and push datafiles directly from the assistant. This integration streamlines workflows for developers, data analysts, and other users by allowing them to perform database queries, manage data, and interact with APIs within the context of their development environment. The server supports both SSE and STDIO modes, offering flexibility for different client architectures and use cases.

List of Prompts

• Query Tinybird Data Sources: A prompt template that enables users to query Tinybird data sources via the Tinybird Query API.

List of Resources

(No explicit resources are listed in the provided information.)

List of Tools

• Query Tinybird Data Sources: Allows execution of queries against Tinybird data sources using the Query API.
• Get Tinybird API Endpoint Results: Fetches results from existing Tinybird API endpoints via HTTP requests.
• Push Datafiles: Enables uploading datafiles to Tinybird.

Use Cases of this MCP Server

• Data Analytics & Exploration: Developers can query and analyze data stored in Tinybird directly from their AI assistant, streamlining data-driven decision-making.
• API Integration: Easily retrieve results from Tinybird API endpoints, simplifying the integration of analytics into other applications or dashboards.
• Automated Reporting: Use the AI assistant to generate and deliver periodic analytics reports by querying Tinybird data sources.
• Data Ingestion & Management: Push new datafiles to Tinybird for real-time analytics, allowing for quick updates and iterative analytics workflows.
• Workflow Automation: Combine querying, pushing, and retrieving data for end-to-end automation of data workflows within development environments.

How to set it up

Windsurf

(No information provided.)

Claude

1. Prerequisites: Ensure you have a Tinybird Account & Workspace, Claude Desktop, and uv installed.
2. Locate Configuration File:
   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json
3. Add Tinybird MCP Server: Paste the following into your config file, replacing placeholder values:

   {
       "mcpServers": {
           "mcp-tinybird": {
               "command": "uvx",
               "args": [
                   "mcp-tinybird",
                   "stdio"
               ],
               "env": {
                   "TB_API_URL": "<TINYBIRD_API_URL>",
                   "TB_ADMIN_TOKEN": "<TINYBIRD_ADMIN_TOKEN>"
               }
           }
       }
   }
   

4. Save and Restart: Save the file and restart Claude Desktop.
5. Verify: Ensure the server connects and is available in Claude.

Securing API Keys

Environment variables are used for API keys. Example:

"env": {
    "TB_API_URL": "<TINYBIRD_API_URL>",
    "TB_ADMIN_TOKEN": "<TINYBIRD_ADMIN_TOKEN>"
}

Cursor

(No information provided.)

Cline

(No information provided.)

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-tinybird": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcp-tinybird” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

A quick assessment: Tinybird MCP Server provides clear setup instructions for Claude and basic tool descriptions, but lacks explicit resource documentation and cross-platform setup details. Its toolset is focused and practical for Tinybird workflows, but the absence of resource and sampling info limits advanced MCP scenarios.

MCP Score

Rating:
Based on the information provided and the tables above, I would rate this MCP server a 6/10. It is solid for Tinybird users with good basic integration and security practices, but missing some documentation and advanced MCP features.