{"repo":"dlt-hub/dlt-mcp","free":true,"listed":false,"github":"https://github.com/dlt-hub/dlt-mcp","clone":"git clone https://github.com/dlt-hub/dlt-mcp.git","description":"MCP server for the Python library dlt","language":"Python","stars":10,"topics":["data-engineering","dlt","elt","etl","mcp","python"],"license":"Apache-2.0","category":"data-pipelines","readme_excerpt":"data load tool (dlt) — MCP Server 🚀 Follow this guide to create a dlt pipeline in 10mins with AI How is it useful? Large language models (LLMs) know a lot about the world, but nothing about your specific code and data. The Model Context Protocol (MCP) server allows the LLM to retrieve up-to-date and correct information about your dlt pipelines, datasets, schema, etc. This significantly improves the development experience in AI-enabled IDEs (Copilot, Cursor, Continue, Claude Code, etc.) Installation The package manager uv is required to launch the MCP server. Add this section to your MCP configuration file inside your IDE. Add your destination(s) in the extras dlt-mcp[...] [!NOTE] The configuration file format varies slightly across IDEs Features Tools The dlt MCP server provides tools that allows the LLM to take actions: - list pipelines : Lists all available dlt pipelines. Each pipeline consists of several tables. - list tables : Retrieves a list of all tables in the specified pipeline. - get table schemas : Returns the schema of the specified tables. - execute sql query : Executes a SELECT SQL statement for simple data analysis. - get load table : Retrieves metadata about data loaded with dlt. - get pipeline local state : Fetches the state information of the pipeline, including incremental dates, resource state, and source state. - get table schema diff : Compares the current schema of a table with another version and provides a diff. - search docs : Searches over the dlt ","default_branch":null,"files":null,"tree":[],"storefront":"/r/dlt-hub","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/dlt-hub/dlt-mcp/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}