High-risk tools in ML Jupyter MCP
11 of the 26 tools in ML Jupyter MCP are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
execute_codeExecuteExecute Python code in a persistent Jupyter kernel.
-
jupyter_ensure_dependenciesExecutejupyter_ensure_dependencies
-
jupyter_execute_cellExecutejupyter_execute_cell
-
jupyter_execute_magicExecutejupyter_execute_magic
-
jupyter_execute_notebookExecutejupyter_execute_notebook
-
jupyter_initializeExecutejupyter_initialize
-
jupyter_profile_codeExecutejupyter_profile_code
-
jupyter_run_fileExecutejupyter_run_file
-
jupyter_setup_uv_environmentExecutejupyter_setup_uv_environment
-
jupyter_sync_environmentExecutejupyter_sync_environment
-
jupyter_validate_setupExecutejupyter_validate_setup
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.