High-risk tools in Python

High severity Python MCP Server 9 of 14 tools

9 of the 14 tools in Python 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

conda Execute

Runs conda commands (list, info, env-list, create, remove, update) and returns structured JSON output.
mypy Execute

Runs mypy and returns structured type-check diagnostics (file, line, severity, message, code).
pip-install Execute

Runs pip install and returns a structured summary of installed packages. WARNING: may execute untrusted code.
poetry Execute

Runs Poetry commands and returns structured output. Supports install, add, remove, show, build, update, lock, check, and export actions.
pyenv Execute

Manages Python versions via pyenv.
pytest Execute

Runs pytest and returns structured test results (passed, failed, errors, skipped, failures).
ruff-check Execute

Runs ruff check and returns structured lint diagnostics (file, line, code, message).
uv-install Execute

Runs uv pip install and returns a structured summary of installed packages. WARNING: may execute untrusted code.
uv-run Execute

Runs a command in a uv-managed environment and returns structured output.

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.

High-risk tools in Python

Tools at high risk

Attacks that target this class

More on Python

Enforce policy on every Python tool call.