Best MCP Servers for Data Science (2026)
The best MCP servers for data science — give AI agents tools to run notebooks, execute Python, analyze datasets, and generate charts as part of an analysis workflow.
Browse all Data Science servers →- 1Bundler MCPsubelskyMost popular in this category on AllMCPs2 0 0
- 2Growthbook MCPgrowthbookCommunity pick3 0 0
- 3Fermat MCPabhiphileCommunity pick3 0 0
- 4Jupyter Notebook MCPjjsantos01Community pick3 0 0
- 5Vizro MCPmckinseyCommunity pick5 0 0
- 6Markdownify MCPzcaceresCommunity pick3 0 0
- 7Jupyter MCP ServerdatalayerCommunity pick2 0 0
- 8OraclawWhatsonyourmindCommunity pick5 0 0
- 9DingoDataEvalCommunity pick3 0 0
- 10MCP Server Data Explorationreading-plus-aiCommunity pick2 0 0
Which Data Science MCP server should you use?
When choosing a Model Context Protocol server for Data Science, select verified or official listings if you need strict API security guarantees. For rapid local dev testing with Claude or Cursor, community-maintained tools offer zero-setup configuration blocks ready to copy-paste.
Frequently asked questions about Data Science MCP servers
What are the best MCP servers for data science?
Servers that run Python, Jupyter, or dataframe operations are the most installed. This page ranks data-science MCP servers by real usage across the AllMCPs directory.
Can an MCP server run Python code for analysis?
Yes — code-execution and notebook MCP servers let an agent run Python in a sandboxed kernel and return results, tables, and plots. Run them in an isolated environment, not against production systems.
Can these generate charts and visualizations?
Several return rendered charts or the data behind them, so an agent can visualize a dataset and hand you back an image or a reproducible script.