Ext Ops Panel
Open dashboard
Comparison

Keboola vs Datacube Sk

Keboola is an MCP server published by keboola. Marketplaces we read that list it: 1 (Docker MCP Catalog). Datacube Sk is an MCP server published by pipeworx-io. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-10. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceKeboolaDatacube Sk
Docker MCP Catalog Listed
Version: sha256:1089ff9910ee
Forks (GitHub): 23
Pulls (Docker Hub): 14 383
Stars (Docker Hub): 0
Stars (GitHub): 85
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.2.1
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

Keboola vs Datacube Sk
FactKeboolaDatacube Sk
Marketplaces that list it11
Stars (GitHub) (differs)85 (better)0 (worse)
Pulls (Docker Hub) (differs)14 383No figure on Docker Hub
Forks (GitHub) (differs)23 (better)0 (worse)
Last release (differs)Not published2026-10-31
Where it runs (differs)On your machine (mcp/keboola-mcp)Remote server (gateway.pipeworx.io/datacube-sk/mcp)
Transport (differs)stdioStreamable HTTP
Tools it declares (differs)33Not published
Environment variables it asks for (differs)2, secrets among them: 11, secrets among them: 1
Licence (differs)MITNot stated
Repository (differs)github.com/keboola/mcp-servergithub.com/pipeworx-io/mcp-datacube-sk
Changes in the last 7 days00
First seen2026-10-112026-10-11
Endpoint at the last check (differs)no remote endpoint we checkStatus out of date: last check 35 h ago returned HTTP 200

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

Keboola

In its own words, on Docker MCP Catalog:

Keboola MCP Server is an open-source bridge between your Keboola project and modern AI tools.

Datacube Sk

In its own words, on Official MCP Registry:

DATAcube — Statistical Office of the Slovak Republic (data.statistics.sk).

How to run each

Keboola As a local MCP server: Docker image

Claude Code
claude mcp add --env "KBC_STORAGE_TOKEN=<YOUR_KBC_STORAGE_TOKEN>" --transport stdio keboola-mcp -- docker run -i --rm -e KBC_STORAGE_TOKEN mcp/keboola-mcp

Requires: KBC_STORAGE_TOKEN (secret)

Datacube Sk As a remote MCP server

Claude Code
claude mcp add --transport http datacube-sk https://gateway.pipeworx.io/datacube-sk/mcp

Requires: PIPEWORX_API_KEY (secret)

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Only Datacube Sk has a remote endpoint we check. How we check endpoints

Tools each declares

Only Keboola has

  • add_config_row
  • create_config
  • create_flow
  • create_oauth_url
  • create_sql_transformation
  • docs_query
  • find_component_id
  • get_bucket
  • get_component
  • get_config
  • get_config_examples
  • get_flow
Show the remaining 21
  • get_flow_schema
  • get_job
  • get_project_info
  • get_sql_dialect
  • get_table
  • list_buckets
  • list_configs
  • list_flows
  • list_jobs
  • list_tables
  • list_transformations
  • query_data
  • run_job
  • search
  • update_bucket_description
  • update_column_description
  • update_config
  • update_config_row
  • update_flow
  • update_sql_transformation
  • update_table_description

Only Datacube Sk has

  • ai_visibility_check
  • archive_compare
  • archive_evidence
  • ask_pipeworx
  • ask_pipeworx_beta
  • ask_pipeworx_grounded
  • bet_research
  • classify_row
  • company_facts
  • company_register_search
  • compare_entities
  • dataset_dimensions
Show the remaining 35
  • deep_research
  • discover_tools
  • entity_profile
  • forget
  • generate_llms_txt
  • get_data
  • kalshi_weather_edge
  • list_datasets
  • list_subscriptions
  • pipeworx_feedback
  • pipeworx_trending
  • polymarket_arbitrage
  • polymarket_edge_tracker
  • polymarket_edges
  • polymarket_fill_risk
  • polymarket_kalshi_spread
  • prediction_calibration
  • recall
  • recent_alerts
  • recent_changes
  • release_calendar_markets
  • remember
  • research_row
  • resolution_audit
  • resolution_diff
  • resolve_entity
  • scan_competitor_ai_presence
  • scan_dependency
  • search_within
  • subscribe
  • suggest_questions
  • unsubscribe
  • updown_divergence_rate
  • updown_venue_compare
  • validate_claim

Both have

None

Tool names as the marketplaces declare them and as Ext Ops observed them on the endpoints (Datacube Sk as of 2026-10-31). More tools is not better in itself: compare what each needs for the job.

Settings each asks for

Only Keboola asks for

  • KBC_STORAGE_TOKEN (secret)
  • KBC_WORKSPACE_SCHEMA

Only Datacube Sk asks for

  • PIPEWORX_API_KEY (secret)

Settings as each marketplace publishes them. Asking for fewer is not better in itself.

What it can do: Keboola · What it can do: Datacube Sk · Compare two other plugins

Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built