Data engineering MCP servers

A server here data pipelines, ETL, data warehouses, data quality or data catalogs.

Not here: querying a single database.

386servers
205 remote181 localTagged by Odel's AI, which can make mistakes
By GitHub stars, at most two per publisher
  1. Number 1: OpenMetadata@open-metadata/openmetadata-mcpOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.15,421 GitHub stars.
  2. Number 2: Jitsu@jitsu/mcpManage Jitsu data pipelines: destinations, streams, connections, functions, live events.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.5,104 GitHub stars.
  3. Number 3: Microsoft Fabric MCP Server@microsoft/microsoft-fabricMCP tools for interacting with Microsoft Fabric3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.3,744 GitHub stars.

Best fit

191 made for this, ranked by starsRemoteLocal
  1. EdgarTools @dgunning/edgartoolsOpen-source SEC EDGAR toolkit — 13 tools, 7 prompts, every filing type. No API key required.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2,784 GitHub stars.
  2. Marmot Data Catalog @marmotdata/marmotOpen-source data catalog. Search assets, explore lineage, and find ownership.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.620 GitHub stars.
  3. Bagel @extelligence-ai/bagelPlain-English analysis of robotics, drone, and IoT data, with intelligent edge data reduction.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.397 GitHub stars.
  4. walkerOS Source Browser @walkeros/source-browserGenerate, parse, and validate walkerOS data-elb HTML tagging attributes4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.348 GitHub stars.
  5. walkerOS Flow @walkeros/flowBuild, validate, simulate, and deploy walkerOS event pipelines4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.348 GitHub stars.
  6. GeoLens @geolens-io/geolensRead-only access to a self-hosted GeoLens spatial catalog: datasets, features, maps, sandboxed SQL.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.275 GitHub stars.
  7. Fitter @pxyup/fitterTurn any website or API into structured JSON with LLM-authored declarative scraping configs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.133 GitHub stars.
  8. GoldenMatch @benseverndev-oss/goldenmatchFind duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.132 GitHub stars.
  9. GoldenAnalysis @benseverndev-oss/goldenanalysisRead-only cross-cutting analysis, metrics, and reporting across the Golden Suite.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.132 GitHub stars.
  10. Catálogo de fuentes públicas de España @bquantfinance/catalogo-fuentes-publicasFuentes de datos públicos de España verificadas: endpoints, trampas, recetas, identificadores3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.120 GitHub stars.
  11. Keboola MCP @keboola/mcpConnect your AI assistants to Keboola and expose your data, transformations, SQL queries, ...4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.85 GitHub stars.
  12. pdfmux @nameetp/pdfmuxPDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.82 GitHub stars.
  13. Misata: synthetic data library @rasinmuhammed/misataLocal, offline: multi-table synthetic data with joins that hold and exact totals. Seeds databases.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.69 GitHub stars.
  14. ZenML @zenml-io/mcp-zenmlMCP server for discovering, reading, and changing ZenML resources with compact generic tools3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.49 GitHub stars.
  15. foehn @kayhendriksen/foehnAccess Swiss meteorological open data from MeteoSwiss, powered by foehn3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.44 GitHub stars.
  16. IterableData @datenoio/iterabledataStreaming read, convert, and inspect 100+ formats. Install iterabledata[mcp] and run iterable-mcp.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.37 GitHub stars.
  17. Airflow @abhishekbhakat/airflow-mcp-serverAn MCP server for Apache Airflow5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.33 GitHub stars.
  18. CLIO Jarvis @iowarp/jarvis-mcpJARVIS-CD MCP with a compact user pipeline contract and explicit admin compatibility profiles6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
  19. CLIO Ndp @iowarp/ndp-mcpNational Data Platform (NDP) MCP server for searching and discovering datasets across multiple...6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
  20. DBConvert Streams (Federated SQL) @dbconvert/streamsRead-only SQL across your PostgreSQL, MySQL, S3 buckets and local data files, in one query.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.24 GitHub stars.
  21. mq-bridge-app @marcomq/mq-bridge-appMove data between 15+ databases, queues and files at high throughput, without it entering context4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.24 GitHub stars.

Also touches on Data engineering

172 where it is one part of a bigger job