duckle MCP Server
slothflowlabs/duckle
[](https://agentrank-ai.com/tool/slothflowlabs--duckle/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Open-source ETL/ELT you deploy on your own servers or cloud. Built on DuckDB: no-code/low-code visual pipelines or SQL, 385 components, dbt, CDC, data quality, reverse ETL, lineage, MCP for AI agents. No vendor cloud, no per-row billing.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
slothflowlabs/duckle is a Rust tool licensed under Apache-2.0. Open-source ETL/ELT you deploy on your own servers or cloud. Built on DuckDB: no-code/low-code visual pipelines or SQL, 385 components, dbt, CDC, data quality, reverse ETL, lineage, MCP for AI agents. No vendor cloud, no per-row billing. Topics: data-engineering, data-integration, data-pipeline, data-quality, duckdb, elt, etl, cdc, connectors, dbt, no-code, data-transformation, reverse-etl, data-orchestration, lakehouse, low-code, mcp, open-source, self-hosted, kubernetes.
Ranked #434 out of 24846 indexed tools.
In the top 2% of all indexed tools.
Has 1,501 GitHub stars.
Has 13 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
1,501 stars → well-known project
Last commit 2d ago → actively maintained
170/246 issues closed → decent issue management
13 contributors → active community
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/slothflowlabs--duckle/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/slothflowlabs--duckle/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/slothflowlabs--duckle" alt="AgentRank"></a> Matched Queries
From the README
<div align="center"> <h3>Pipelines you own. Author and deploy to your servers or cloud.</h3> <p><b>Duckle</b> is an open-source ETL platform for teams who want their pipelines running on their own infrastructure. Author on a canvas, in Python or in SQL, then ship the same file to your own server or cloud account: <code>duckle-runner serve</code> runs it headless on a schedule, in Docker or on a box you own, with a web console, roles and an audit trail. Every pipeline is one file in git, so it outlives whoever wrote it. It compiles to SQL on DuckDB and uses every core you give the box, so a bigger instance is a faster pipeline: <b>96 million rows out of Postgres to Parquet in 39.9s</b>. <b>No vendor cloud. No per-row billing. No lock-in.</b></p> <a href="https://duckle.org/"></a> <p><sub><i>Duckle is an independent open-source project by SlothFlowLabs. It builds on the DuckDB engine but is not part of, affiliated with, or endorsed by DuckDB Labs or MotherDuck.</i></sub></p> <p> <aRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.