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

Best fit

191 made for this, ranked by starsRemoteLocal
  1. Etld @pablixnieto2/etld-mcp-serverDeterministic B2B Data Middleware. Waterfall parsing for CSV, EDI, SEC & Finance. No hallucinations.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
  2. Fivetran @yimingyan/fivetran-mcpMCP server for Fivetran API - manage syncs, check status, and control data pipelines5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
  3. BankSync @banksync/mcpConnect AI agents to bank accounts, transactions, balances, and investments.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
  4. GTFS Scorecard @chelseakr/gtfs-scorecardRead-only GTFS transit feed scorecards: grades, plain-language fixes, and history.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  5. Harvest @the-warl0ck/harvest-mcpPlain-English training-data scout: 12 experts sweep HuggingFace + GitHub, compose scored packs.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  6. Transform Rules MCP Server @vinhphatfsg/transform-rules-mcpMCP server for CSV/JSON data transformation using YAML rules4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
  7. NetCafe Tables @ainetcafe/netcafe-tablesMessy spreadsheets in, clean checkable tables out. Every result carries its arithmetic proof.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  8. Telegram Channel Scraper - Posts, Media & Buttons | No Login @anshumanatrey/telegram-channel-scraperTelegram Channel Scraper - No Login, $0.30 per 1K Posts14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  9. NicheDB @nichedb/nichedbSources in, feeds out: an open, ever-growing database of real-time public data, enriched.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  10. Debezium @dockndevai/mcp-debeziumDebezium / Kafka Connect CDC connector management for AI agents — governed, secret-safe.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  11. iceDQ Tools MCP @icedq-tools/mcp-serverMCP Server for iceDQ Data Reliability Platform5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  12. Data Profiler @ridadata/mcp-data-profilerProfile local CSV, Parquet, JSON and Excel files into a compact data-quality summary.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  13. acikpoz @gulmezeren2-byte/acikpozTurkish public construction unit-price (birim fiyat) catalog PDFs into structured pozes4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  14. Rulemorph MCP Server @vinhphatfsg/rulemorph-mcpMCP server for CSV/JSON data transformation using YAML rules4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
  15. Quorel @var-raphael/quorelTurn any public website into a clean, versioned, queryable API — with native MCP support.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  16. FastTransfer @arpe-io/fasttransfer-mcpMCP server for FastTransfer — high-performance parallel data transfer between databases5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  17. LakeXpress @arpe-io/lakexpress-mcpMCP server for LakeXpress — automated database-to-cloud data pipeline as Parquet4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  18. Docpick @arknill/docpickSchema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  19. AnomalyArmor @anomalyarmor/armor-mcpData observability tools for engineering teams: alerts, freshness, schema drift, lineage, quality.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
  20. Shadowjoin @harsh-chandak/shadowjoinMeasure the matches your exact join is silently dropping, and get the rule that fixes each.Not assessed yet.Runs on your machine, installed from npm.
  21. CloudCrane workspace @cloudcrane/workspaceRead and build a CloudCrane workspace: datasets, field contracts, review queue, receipts, runs.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  22. IndieML Substance API @ezchx/indiemlScores text for substance, depth, and clarity in under 25ms.Not assessed yet.A remote server; it needs your API key.
  23. Estuary Flow MCP by usefulapi @usefulapi/estuary-flowInspect Estuary Flow captures, materializations, collections and stats.Not assessed yet.A remote server; no sign-in.
  24. Arkrel @arkrel/arkrelTurn documents into verified, structured data: fields, tables, and automatic checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.