- Conduid
- Marketplace
- #data-engineering
MCP servers tagged data-engineering
151 live MCP servers tagged "data-engineering", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with data-engineering.
Cronova
Lightweight self-hosted workflow scheduler in a single Go binary — an open-source Airflow/Azkaban alternative. Embedded SQLite, DAGs (cron + dependencies + backfill), polyglot tas…
Repairpilot
DataHub-powered incident-to-repair autopilot: block, repair, prove, remember.
The Skills Barn
326 open, production-ready Agent Skills for the tasks language models can't do reliably from training alone. Free · Apache 2.0.
Schemadrift
Schema-change detector and data-contract tests
Kion Clickhouse Analytics
Conversational OTT/streaming analytics: KPI dashboards over 5.4M viewing events in ClickHouse Cloud, queried in natural language via LibreChat + Model Context Protocol (MCP), visu…
Flowproxy
Self-hosted dbt-core + MetricFlow semantic layer proxy. Query governed metrics from Amazon QuickSight and LLM agents over the PostgreSQL wire protocol, with guardrails enforced. A…
Marketing Postgres Server
Read-only MCP server exposing marketing analytics to AI assistants via PostgreSQL
Etl Archaeologist
AI agents that document & rationalise legacy SAP BODS ETL for migration to Glue/dbt
Mango
Free-data market providers, historical-context analytics, and a self-grading prediction ledger. Built while learning.
Fde Casebook
Four engineering case studies written for forward-deployed engineering roles - including the work I built and then deliberately killed. u9762u5411 FDE u5c97u4f4du7684u5de5u7a0bu68…
Operator Etl
Agentic ETL pipeline for FOIA & public comments — LangGraph, MCP, PII vault, Medallion warehouse (DuckDB/BigQuery)
Embedaudit
Embedding / vector-store drift and poisoning audit
Lineagemap
Column-level lineage extracted from SQL and dbt
Autotwin De
Intelligent digital twin for German electric mobility: official open data, a physics simulation of vehicles, PostGIS analytics, an ML energy model, charging optimisation and an MC…
Duckdb Analytics MCP
Read-only analytics MCP server over DuckDB: semantic layer that prevents wrong answers, token-efficient output (-61% vs JSON), and a parser-based SQL guard.
Premortem Datahub
Premortem — how it breaks, before you merge (DataHub schema-change rehearsal)
Data Engineering MCP Server
Official MCP Python server exposing typed data-engineering tools, resources, prompts, read-only SQL, and synthetic ETL investigations.
Competitive Pricing Agent
Always-on autonomous e-commerce pricing agent on AWS — a 14-tool Amazon Bedrock ReAct agent that senses sales & competitor data, reasons, acts, and learns (epsilon-greedy). Includ…
CogniMesh
Intelligent data mesh for AI agents. Declarative use-case registry, self-improving Gold layer, MCP-native.
Gcp Data Pipeline Security Monitoring
GCP data pipeline for security monitoring — ingests events via CSV or Pub/Sub, validates and loads them into BigQuery (raw → cleaned → aggregated). Orchestrated with Airflow, de…
WorldEconomy
World Economy Lab - economics from primary data: a DuckDB warehouse (year 1 CE to 2101, 26 sources, ~14.9M observations), a fully computed chaptered report, and an MCP query appar…
Spendiq Prototype
Conversational AI copilot over procurement, AP, and contract data — grounded answers with citations to specific rows and clauses. Built for the TechTorch AI & Data Engineer challe…
AI Based Data Engineering
Companion code for AI-Based Data Engineering (Packt) by Richie Bachala: runnable examples, the OpsPulse dataset generator, and per-chapter code for building the data platform AI a…
Combined Agent Kit
Claude Code plugin, agent skills and runnable SQL examples for CRM, billing and business-data analysis with Combined
Praxis Datahub
Evidence-bound remediation agent for DataHub-governed data products. Turns one schema-drift incident into a proof-carrying, verified dbt change set — with an MCP server and a Data…
Sqlproctor
Deterministic semantic verification for agent-generated SQL.
OpenBB ODP
Open Data Platform for analysts, quants and AI agents.
Clickhouse Kit
ClickHouse for coding agents: MCP wiring from environment variables, a query-hygiene skill, and guard hooks against inflated counts and full-history scans.
Commerce Data Platform
Assembles the operational context a business question needs — and names what is missing. PostgreSQL, Context Engine, FastAPI/MCP, React inspector.
Bounded Retrieval
Demonstration of efficient MCP tools for investigating large conversational datasets
Blackout
Chaos engineering for your data stack — powered by the DataHub context graph.
Datadef MCP
Data-architecture diagrams your AI generates, edits, and exports. Remote MCP server for Claude, Cursor, VS Code, Gemini CLI.
MartyStev
Data Engineer • Data Platform Architect • Creator of OctaSQL & ClawMux
CityScope
Evidence-grounded geospatial intelligence for London cycling, powered by Gemini, MCP, and Google Cloud.
Forest1
Ask in plain English about 24 years of Global Forest Watch data — 165 countries & 2,779 regions. MCP server with 17 query tools + a live natural-language Streamlit demo. Python ·…
DataEngineeringSeniorProject
A production-style data platform that ingests from three heterogeneous sources (PostgreSQL, MongoDB, REST API), loads into Snowflake, transforms through dbt staging and intermedia…
AI Engineering Portfolio
Anonymized AI engineering portfolio: backend Python, data extraction, AI analysis, and ChatGPT Apps
ImpactLint
Metadata-aware data change reviews powered by DataHub MCP and Paritok
Known Path
Light only the trusted catalog assets for a data job — then leave the route behind. DataHub Agent Hackathon.
Agriculteur
Terroir Context Agents — agent de conseil de semis alimenté par un graphe de contexte DataHub (hackathon Build with DataHub).
Datapact
Offline data-contract runtime: lint an ODCS contract and validate a CSV against it, in your browser or CI.
Reconmind
Multi-agent, RAG-powered copilot that investigates data pipeline incidents (key drift, duplicate submissions, schema drift, volume anomalies) and writes the incident report.
DataOps Investigator
Evidence driven AI agent for investigating data system incidents using LLM planning, MCP-based evidence collection, and deterministic root-cause analysis.
Analytics Evals
Agent skills for testing analytics and text-to-SQL agents: mine golden test cases from your query history, score with pass^k and confidence intervals, and find which context files…
Integrations
Emolysis integrations for Claude Code, Cursor, Codex and other MCP clients
.github
Website and central hub for the SBDK ecosystem - five open-source reference implementations demonstrating how to build local-first data and AI tools (data pipelines, ML inference,…
Muster
A search index over Australian data roles, pulled straight from employers' ATS feeds
Consolidation Erp MCP
Odoo + FEC ledger + warehouse API consolidated in DuckDB; SQL three-way-match controls recover all 22 planted discrepancies; LLM agent queries it via MCP
Awesome Google Trends MCP
A curated plain-English index of Model Context Protocol (MCP) servers, autonomous agent tools, scrapers, and data pipelines for Google Trends.
Data Foundry
An AI-native data foundry: turns messy, lawfully acquired sources into canonical, evidence-backed knowledge products served via web, REST, MCP and bulk exports. Provenance-first,…