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. Wever World Data @weverpay/world-dataDiscover Wever services, process data, and delegate checked results between agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. OutSend @outsend/outsendFind local businesses, enrich them with emails and socials, and run lead pipelines from your AI.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  3. Mostly Right @mostlyright/datasetsSearch, sample and query open reproducible datasets published as immutable Parquet with schemas.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. ParquetHarmonize @tfitzgerwitness/parquetharmonizeHarmonize Parquet schemas; ordinary unions are free, residual reconciliation is x402-gated.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. Internet Janitor @capneura/internet-janitorDeterministic cleanup tools for decimals, whitespace, filenames, delimiters, and booleans.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. CSV Import Rehearsal @mcpscores/csv-import-rehearsalSimulate a CSV import against a supplied typed column contract and return exact accepted rows, re...6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Postgres Kafka Stack Generator @getvda/postgres-kafka-stack-generatorPostgres + Kafka Stack Generator7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. HumanMirror Outcome @humanmirror/outcomeVerified AI-agent outcomes: secret scanning, JSON cleanup, dedupe, anomaly and schema checks.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. HumanMirror Forge @humanmirror/forgeFive deterministic micro-tools for AI-agent data pipelines: clean, dedupe, normalize, score, detect.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. AgentNative: Public Data, Government Datasets, Federal Statistics & Official Records @cazimedia/data-exchangeNormalized official data with provenance, aggregations, insights, free samples and agent access.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. AgentNative: Public Data, Government Datasets, Federal Statistics & Official Records @cazimedia/government-public-open-data-datasets-federal-state-city-statistics-census-records-police-education-schoolsNormalized official data with provenance, aggregations, insights, free samples and agent access.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Tools @streamkap/toolsStreamkap CLI & MCP server - manage CDC pipelines, sources, destinations, and transforms9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  13. DBMigratePro Continuous Migration @provydon/dbmigratepro-continuous-migrationKeep a target database continuously in sync with a source on another provider, then promote it.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  14. Data Quality Gate - deterministic post-scrape cleaner + verdict @aidatatools-dev/data-quality-gatePost-scrape data cleaner, no LLM: repairs mojibake, HTML, invisible chars. Plus a verdict.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. US Brand Intelligence @timzinin/us-brand-intelligencePay-per-call US brand evidence and signal workflows with free MCP discovery and x402 payments.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. Datadef MCP @datadef/mcpGenerate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. Entity Resolve @x402supply/entity-resolveFuzzy entity resolution and dedupe for names, addresses, and company records. $0.02/call via x402.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. Atlasemoji @atlasemoji/mcpAI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  19. Oleander @oleander/oleanderThe all-in-one data stack for agents. Upload files, run SQL, evolve tables, and render charts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  20. WaveHouse Cloud @wavehouse/mcpBrowse, query, and administer your managed WaveHouse + ClickHouse projects (schema, pipes, policy).8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  21. Sidecar @sidecardata/sidecarCross-tool context for your data stack. Search, lineage, and impact across warehouse and BI tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  22. dynamical.org Weather & Climate Catalog @dynamical-org/mcpSearch dynamical.org's open STAC catalog of weather & climate datasets (GFS, ECMWF, HRRR).2% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. MC-Data Monitor @evozim/mc-data-monitorSQL pipeline observability and DBT integration monitor.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  24. Data Observability @evozim/data-observabilitySQL data health analyzer and pipeline observability evaluator.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.