Sqrl
Data Pipeline Automation Framework to build MCP servers, data APIs, and data lakes with SQL.
What is Sqrl?
Sqrl is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to data pipeline automation framework to build mcp servers, data apis, and data lakes with sql.
Data Pipeline Automation Framework to build MCP servers, data APIs, and data lakes with SQL.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Data Pipeline Automation Framework to build MCP servers, dat
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx sqrlConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Sqrl
DataSQRL is a data pipeline automation framework that lets you build MCP servers, data APIs, and data lakes using SQL. It compiles SQL scripts into deployable streaming data pipelines backed by Apache Flink, Kafka, and PostgreSQL, and automatically generates MCP tool definitions, REST API endpoints, and GraphQL schemas from the same SQL source. Developers use it to expose real-time data processing pipelines as AI-accessible MCP tools without writing infrastructure glue code.
Prerequisites
- Docker installed and running (DataSQRL is distributed as a Docker image)
- Docker Compose for multi-service deployments
- An MCP-compatible client such as Claude Desktop or Cursor
- Basic familiarity with SQL for writing SQRL scripts
- Sufficient memory for running Flink and Kafka containers (at least 8 GB RAM recommended)
Initialize a new DataSQRL project
Use the DataSQRL Docker image to scaffold a new project from a template. The 'api messenger' template creates a messaging data pipeline project.
docker run --rm -v $PWD:/build datasqrl/cmd init api messengerInspect and edit the generated SQL scripts
DataSQRL generates SQRL files that define your data pipeline logic using SQL. Edit these files to add your own data processing, aggregations, and API definitions.
Compile the project to deployment artifacts
Compile the SQRL scripts into deployment artifacts including Flink execution plans, Kafka topic schemas, PostgreSQL definitions, server queries, MCP tool specifications, and GraphQL models.
docker run --rm -v $PWD:/build datasqrl/cmd compile messenger-prod-package.jsonRun the data pipeline
Start the runtime environment. The stack exposes a GraphQL API on port 8888, a REST API on port 8081, and an MCP endpoint at /v1/mcp.
docker run -it --rm -p 8888:8888 -p 8081:8081 -v $PWD:/build datasqrl/cmd run messenger-prod-package.jsonRun tests against the generated artifacts
Validate your pipeline logic using the built-in test runner.
docker run -it --rm -v $PWD:/build datasqrl/cmd test messenger-test-package.jsonConnect your MCP client to the DataSQRL MCP endpoint
Configure your AI assistant to connect to the DataSQRL MCP server at http://localhost:8081/v1/mcp (HTTP/SSE). The generated MCP tool definitions describe all available data operations.
{
"mcpServers": {
"datasqrl": {
"url": "http://localhost:8081/v1/mcp"
}
}
}Sqrl Examples
Client configuration
Connect Claude Desktop or Cursor to a running DataSQRL MCP server using the HTTP/SSE endpoint generated by the platform.
{
"mcpServers": {
"datasqrl": {
"url": "http://localhost:8081/v1/mcp"
}
}
}Prompts to try
Once connected to a DataSQRL MCP server, the AI can query and interact with your data pipelines.
- "What data tools are available in this DataSQRL pipeline?"
- "Query the latest messages from the messenger pipeline."
- "Show me the aggregated event counts for the past hour."
- "Call the data API to retrieve all active user sessions."
- "What MCP tools did DataSQRL generate for the messenger project?"Troubleshooting Sqrl
Docker containers fail to start due to insufficient memory
DataSQRL's stack includes Flink and Kafka which require significant memory. Allocate at least 8 GB to Docker in Docker Desktop settings under Resources.
Compilation fails with an error about an invalid package JSON
Ensure your package JSON file (e.g., messenger-prod-package.json) exists in the current directory and is correctly formatted. Run from the project root where the file resides.
MCP endpoint returns 404 at /v1/mcp
The MCP endpoint is only available after running the compiled artifacts with datasqrl/cmd run. Ensure the run command completed successfully and both ports 8888 and 8081 are published.
Frequently Asked Questions about Sqrl
What is Sqrl?
Sqrl is a Model Context Protocol (MCP) server that data pipeline automation framework to build mcp servers, data apis, and data lakes with sql. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Sqrl?
Follow the installation instructions on the Sqrl GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Sqrl?
Sqrl works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Sqrl free to use?
Yes, Sqrl is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Sqrl Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Sqrl? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Sqrl in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Sqrl?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.