
pandas-doctor
Finds slow pandas code, checks rewrites give identical results on your data, measures speedups.
- tools
- 3
- transport
- STDIO
- last updated
- Nov 12, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
check_codeFinds slow pandas patterns in code and suggests rewrites.
Finds slow pandas patterns in code and suggests rewrites.
No parameter schema in public metadata yet.
verify_rewriteVerifies that a candidate rewrite gives the same result as the original on the given setup data.
Verifies that a candidate rewrite gives the same result as the original on the given setup data.
No parameter schema in public metadata yet.
list_rulesLists the pandas-doctor rules.
Lists the pandas-doctor rules.
No parameter schema in public metadata yet.
Sponsors
Readme
pandas-doctor
pandas-doctor finds the slow pandas lines in your code, rewrites them, and checks on your own data that the result is exactly the same. Then it tells you how much faster the rewrite was, measured, not guessed.

That's a real run on real data: examples/taxi/features.py on January 2024 of the NYC TLC yellow taxi trips (2.96 million rows), with the kind of loops a lot of notebooks have. The script took 96.6 s (M4 Pro, pandas 3.1.0 with pyarrow). pandas-doctor checked 5 rewrites on the script's own data, all identical and faster. After --fix the whole script runs in 1.64 s and prints exactly the same output. Full report in docs/taxi-run-full.txt.
Details
- Repository
- github.com/furqan-khan07/pandas-doctor
- Category
- Data & Analytics
- Package
pandas-doctor- Transport
- STDIO
- Registry
- MCP registry, active