data engineering mcp servers

r3dz4r/datapulse-my

MCP server Claude CodeCodexCursor

Read-only discovery for 389 Malaysian public datasets with freshness, licence, and provenance. Remote server at mcp.data-pulse.my.

wesseltl/data-cleaner-agent

MCP server Claude CodeCodexCursor

Clean messy CSVs with an agentic workflow: an LLM decides the steps, tested code does the work. Runs locally from the agentic-csv-cleaner Python package.

atharvpatwardhan/MCP-Server-for-ETL-Orchestration

MCP server Claude CodeCodexCursor

MCP server "airflowOrchestrator" as configured in atharvpatwardhan/MCP-Server-for-ETL-Orchestration. Runs local_project_path/mcp_server/main.py with python.

arthurxavier106/duckdb-analytics-mcp

MCP server Claude CodeCodexCursor

MCP server "duckdb-analytics-mcp" as configured in arthurxavier106/duckdb-analytics-mcp. Runs locally from the duckdb-analytics-mcp Python package.

surajpanwar/advanced-calc-engine

MCP server Claude CodeCodexCursor

MCP server "advanced-calc-engine" as configured in surajpanwar/advanced-calc-engine. Runs locally from the advanced-calc-engine Python package.

owieschon/contact-verifier

MCP server Claude CodeCodexCursor +2

MCP server "contact-verifier" as configured in owieschon/contact-verifier. Runs locally from the contact-verifier Python package.

debabsah/sqlproctor

MCP server Claude CodeCodexCursor +2

Deterministic semantic verification for agent-generated SQL. Runs locally from the sqlproctor Python package.

SeraKah-1/known-path

MCP server Claude CodeCodexCursor +2

MCP server "known-path" as configured in SeraKah-1/known-path. Runs locally from the known-path Python package.

neocatalystlabs/semlayer

MCP server Claude CodeCodexCursor +2

Open semantic layer format and inference engine for data warehouses. Runs locally from the semlayer Python package.

tlouvart/datadef-mcp

MCP server Claude CodeCodexCursor +2

MCP server "datadef", hosted remotely at datadef.io, as configured in tlouvart/datadef-mcp.

Roberton003/databricks-capstone-delivery

MCP server Claude CodeCodexCursor +2

MCP server "databricks-capstone-delivery" as configured in Roberton003/databricks-capstone-delivery. Runs locally from the databricks-capstone-delivery Python package.

chakri192/ripple

MCP server Claude CodeCodexCursor +2

Python client for rippled. Runs locally from the ripple Python package.

khaosans/operator-etl

MCP server Claude CodeCodexCursor +2

MCP server "operator-etl" as configured in khaosans/operator-etl. Runs locally from the operator-etl Python package.

NetApp/aide-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for NetApp AI Data Engine. Runs locally from the netapp-aide-mcp Python package.

arpe-io/migratorxpress-mcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for MigratorXpress, enabling database migration between heterogeneous database systems. Runs locally from the migratorxpress-mcp Python package. Needs 4 environment variables to run.

benseverndev-oss/goldenpipe

MCP server Claude CodeCodexCursor +2

Pluggable pipeline framework for data quality workflows. Runs locally from the goldenpipe Python package.

gauthierpiarrette/datadiffer

MCP server Claude CodeCodexCursor +2

Diff two tables and see what changed and which slice of your data it is concentrated in. A maintained successor to data-diff. Runs locally from the datadiffer Python package. Needs 1 environment variable to run.

kroq86/data-engineering-runtime-lab

MCP server Claude CodeCodexCursor +2

MCP server "mini-data-engine" as configured in kroq86/data-engineering-runtime-lab. Runs in Docker (${workspaceFolder}/tests/artifacts:/app/tests/artifacts).