Jupyter MCP vs MCP Python Interpreter
Both are data & notebooks MCP servers, and we ran both through the same test (run cell) in each app. Jupyter MCP passed 3 of 4 apps we tested it in; MCP Python Interpreter passed 0 of 3.
Test results side by side
| Jupyter MCP | MCP Python Interpreter | |
|---|---|---|
| Claude Code | Passed 2026-10-21 | Failed 2026-10-15 |
| Cursor | Passed 2026-10-21 | Failed 2026-10-15 |
| Claude Desktop | Passed 2026-10-20 | Not tested yet |
| ChatGPT (Codex) | Failed 2026-10-15 | Failed 2026-10-22 |
| Tools exposed (protocol check) | 18 tools | — |
| GitHub stars | 1,302 | 104 |
| License | BSD-3-Clause | NOASSERTION |
| Last push | 2026-10-11 | 2026-07-02 |
Results from our own harness runs, dated per cell. Stars and last push from GitHub at our last data refresh. We don’t pick a winner here: which one fits depends on your app and setup.
What each does
Jupyter MCP: Run and edit cells in a live Jupyter notebook.
MCP Python Interpreter: Runs Python code and manages Python environments and packages from an agent, inside a working folder.
