data-engineering MCP servers

42 tagged data-engineering, measured the same way as everything else here.

Browse within: data-quality 15ETL 7LLM 7duckdb 7cli 6dbt 6

goldenanalysis

01

benseverndev-oss/goldenmatch

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

Read-only cross-cutting analysis, metrics, and reporting engine for the Golden Suite. Runs locally from the goldenanalysis Python package.

not rated 133 +1 today A tokens not measured original MIT

clarilayer

02

clarilayer/clarilayer

MCP server Claude CodeCodexCursor +2

Individual-analyst context layer: recall, remember, and reconcile your data and engineering context. Remote server at clarilayer.com.

not rated 82 29d ago A tokens not measured

dolphin-mcp-pilot

03

iflytek/dolphin-mcp-pilot

MCP server Claude CodeCodexCursor +2

MCP server "dolphin-mcp-pilot" as configured in iflytek/dolphin-mcp-pilot. Runs in Docker (ghcr.io/iflytek/dolphin-mcp-pilot:0.3.1). Needs 5 environment variables to run.

not rated 19 +1 8d ago A tokens not measured original Apache-2.0

datacharter

04

datacharter/datacharter

MCP server Claude CodeCodexCursor +2

Charter your data — contract-governed local data exploration, powered by DuckDB. Runs locally from the datacharter Python package.

not rated 14 2d ago A tokens not measured original Apache-2.0

datris

05

datris/datris-platform-oss

MCP server Claude CodeCodexCursor +2

MCP server for AI-driven data pipeline operations — ingest, validate, transform, analyze, and query data. Tools covering ETL, AI data quality, vector search, PostgreSQL, MongoDB, Snowflake, Databricks, Kafka, S3/MinIO, HashiCorp Vault, Qdrant, Weaviate, Milvus, Chroma, pgvector. Runs locally from the datris-mcp-server…

not rated 12 today A tokens not measured AGPL-3.0

scherlok

06

rbmuller/scherlok

MCP server Claude CodeCodexCursor +2

A detective for your data. Zero-config data quality monitoring. Runs locally from the scherlok Python package. Needs 1 environment variable to run.

not rated 11 18d ago A tokens not measured original MIT

crocodile

07

nazmiefearmutcu/Crocodile

MCP server Claude CodeCodexCursor +2

Deep Learning Framework & Workload Management For On-premise Personal Machines. Runs locally from the crocodile Python package.

not rated 3 today A tokens not measured original Apache-2.0

semlayer

08

neocatalystlabs/semlayer

MCP server Claude CodeCodexCursor +2

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

not rated 3 yesterday A tokens not measured original Apache-2.0

goldencheck

09

benseverndev-oss/goldencheck

MCP server Claude CodeCodexCursor +2

Data validation that discovers rules from your data so you don't have to write them. Runs locally from the goldencheck Python package.

not rated 2 5mo ago A tokens not measured original MIT archived

seshat-bi

10

Kemetra/Seshat-BI

MCP server Claude CodeCodexCursor +2

Seshat BI: agent-first Retail BI readiness checker (static retail check + live retail validate over the medallion warehouse and Power BI conventions). Runs locally from the seshat-bi Python package.

not rated 2 2d ago A tokens not measured original Apache-2.0

fastbcp-mcp

11

arpe-io/fastbcp-mcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for FastBCP, enabling efficient data export from databases to files. Runs locally from the fastbcp-mcp Python package. Needs 4 environment variables to run.

not rated 2 7mo ago A tokens not measured original MIT

datapulse-my

12

r3dz4r/datapulse-my

MCP server Claude CodeCodexCursor +2

Read-only discovery for 418 Malaysian public datasets with freshness, licence, and provenance. Remote server at mcp.data-pulse.my.

not rated 2 today A tokens not measured original MIT

dagsmith

13

tmcwilliam707/dagsmith

MCP server Claude CodeCodexCursor +2

MCP server "dagsmith" as configured in tmcwilliam707/dagsmith. Runs locally from the dagsmith Python package.

not rated 1 2mo ago A tokens not measured original MIT

goldenflow

14

benseverndev-oss/goldenflow

MCP server Claude CodeCodexCursor +2

Data transformation toolkit — standardize, reshape, and normalize messy data before it hits your pipeline. Runs locally from the goldenflow Python package.

not rated 1 5mo ago A tokens not measured original MIT archived

fasttransfer-mcp

15

arpe-io/fasttransfer-mcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for FastTransfer, enabling efficient data transfer between database systems. Runs locally from the fasttransfer-mcp Python package. Needs 4 environment variables to run.

not rated 1 7mo ago A tokens not measured original MIT

lakexpress-mcp

16

arpe-io/lakexpress-mcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for LakeXpress, enabling database to Parquet export with sync management and data lake publishing. Runs locally from the lakexpress-mcp Python package. Needs 5 environment variables to run.

not rated 1 7mo ago A tokens not measured original MIT

omnidata-mcp

17

MostafaAI10/OmniData-MCP

MCP server Claude CodeCodexCursor +2

MCP server "omnidata-mcp" as configured in MostafaAI10/OmniData-MCP. Runs locally from the omnidata-mcp Python package.

not rated 1 2mo ago A tokens not measured original MIT

praxis

18

Marc-Dvci/praxis-datahub

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "praxis" as configured in Marc-Dvci/praxis-datahub. Runs praxis.mcp with python. Needs 1 environment variable to run.

not rated 0 2mo ago A tokens not measured original Apache-2.0

datanika-mcp

19

datanika-io/datanika-core

MCP server Claude CodeCodexCursor +2

MCP server for Datanika — browse connections, preview data, and manage pipelines from Claude Desktop. Runs locally from the datanika-mcp Python package. Needs 3 environment variables to run.

not rated 0 21d ago A tokens not measured AGPL-3.0

pyspark-mcp

20

AnnasMazhar/pyspark_mcp

MCP server Claude CodeCodexCursor +2

Not the live-Spark pyspark-mcp package — this is SQL→PySpark/Glue codegen. MCP server for SQL migration, AWS Glue job generation, and PySpark optimization. Runs locally from the pyspark-tools Python package.

not rated 0 4d ago A tokens not measured original MIT

infermap

21

benseverndev-oss/infermap

MCP server Claude CodeCodexCursor +2

Inference-driven schema mapping engine. Runs locally from the infermap Python package.

not rated 0 5mo ago A tokens not measured original MIT archived

battery-erp

22

icohangar-ops/battery-erp

MCP server Claude CodeCodexCursor +2

Battery value-chain ERP domain library with optional inventory REST + MCP adapters. Runs locally from the battery-erp Python package. Needs 2 environment variables to run.

not rated 0 22d ago A tokens not measured original MIT

saudeemdado

23

pedropaulofernandes88-stack/saude-publica-br

MCP server Claude CodeCodexCursor +2

Servidor MCP do Saúde em Dado — a saúde do Brasil (DataSUS + IBGE) consultável por IA. Runs locally from the saudeemdado-mcp Python package.

not rated 0 16d ago A tokens not measured

data-cleaner-agent

24

wesseltl/data-cleaner-agent

MCP server Claude CodeCodexCursor +2

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.

not rated 0 2mo ago A tokens not measured original MIT