Server Chart vs Keboola MCP Server

Two MCP servers from our data & analytics ranking, compared on live data - updated nightly, never sponsored.

Bottom line · 2026-09-30

Server Chart records more monthly package installs (15,718 vs 10,396); Keboola MCP Server is maintained more actively (last commit 2026-09-29 vs 2026-08-27).

How they differ in kind

Server Chart focuses on: A Model Context Protocol server for generating charts using AntV. Keboola MCP Server focuses on: Keboola MCP Server is an open-source bridge between your Keboola project and modern AI tools. Keboola MCP Server offers a remote endpoint; Server Chart is local stdio. Environment-variable extraction: Server Chart yielded 3 variables; Keboola MCP Server yielded 4 variables. Implementation languages differ (TypeScript vs Python).

What each one does

Server Chart

A Model Context Protocol server for generating charts using AntV. We can use this mcp server for _chart generation_ and _data analysis_. It runs locally over stdio via the published package.

From the project's README.

Keboola MCP Server

Keboola MCP Server is an open-source bridge between your Keboola project and modern AI tools. It turns Keboola features - like storage access, SQL transformations, and job triggers - into callable tools for Claude, Cursor, CrewAI, LangChain, Amazon Q, and more.

From the project's README.

14 signals, side by side

Signal Server Chart Keboola MCP Server
Monthly installs 15,718 10,396
GitHub stars 4,388 86
Last commit 2026-08-27 2026-09-29
Releases · last 90 days 0 10+
In the registry since Sep 2025 Oct 2025
Registry versions 7 45
Documented tools not extracted - see README not extracted - see README
Env vars extracted 3 4
Runs local (stdio) local or remote
Endpoint auth local only yes (verified)
Maintenance actively maintained actively maintained
License MIT MIT
Language TypeScript Python
Category rank #1 of 86 #2 of 86

Environment variables found in the READMEs

These are extracted names, not a requiredness check. Project docs may mark them optional or require other setup.

Server Chart

  • VIS_REQUEST_SERVER
  • SERVICE_ID
  • DISABLED_TOOLS

Keboola MCP Server

  • KBC_STORAGE_API_URL
  • KBC_BRANCH_ID
  • KBC_STORAGE_TOKEN
  • KBC_PROJECT_ID

Which one, for what

Derived from the signals above, not hands-on testing.

Pick Server Chart if…

  • → you prefer a TypeScript codebase to extend or audit
  • → measured package adoption matters - 15,718 monthly installs

Pick Keboola MCP Server if…

  • → release velocity matters - 10+ releases in 90 days vs 0
  • → you want a hosted endpoint instead of running a local process

Who's behind them

Server Chart - antvis: 1 MCP server tracked, 1 maintained, 4,388 combined stars.

Keboola MCP Server - keboola: 2 MCP servers tracked, 1 maintained, 86 combined stars.

Not sold on either?

The next-ranked data & analytics servers we track:

Quick answers

Is Server Chart better than Keboola MCP Server?

Package installs favor Server Chart: 15,718 monthly installs to 10,396, though Keboola MCP Server has committed more recently (2026-09-29). Keboola MCP Server still ranks #2 of 86 maintained data & analytics servers. Data as of 2026-09-30; we haven't hands-on tested either.

Can I use Server Chart and Keboola MCP Server together?

Yes - MCP clients accept multiple servers in one config, so you can enable both data & analytics servers side by side. If their tools overlap, keep the one whose toolset fits to keep your agent's tool list lean.

What environment variables do their READMEs document?

Server Chart: 3 environment variables extracted from the README setup; Keboola MCP Server: 4 environment variables extracted from the README setup. Extraction does not rule out other authentication or configuration steps; check each project's current documentation.

Keep exploring: best data & analytics servers · TypeScript servers · Python servers · all comparisons · every server

Methodology: package-usage signal = npm/PyPI installs (last month, platform APIs) · maintenance = commit recency + release cadence (GitHub) · tool lists and environment-variable names extracted from each project's README · endpoint auth from our own nightly probes. We haven't hand-tested these servers; everything here is data as of 2026-09-30.