// SCAN REPORT

Python Code Runner

4 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

4 can modify or destroy data

0 read-only

4 tools total

Community server · catalogue entry verified 12/06/2026

How to control Python Code Runner ↓

TOOL MAP

What Python Code Runner exposes to your agents

Read (0) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Python Code Runner tools

Execute · High run_python_code This tool executes arbitrary Python code whose effects are entirely dependent on what code is provided as arguments. Execute · High run_python_file This tool executes arbitrary Python code from a file, which is Execute category. Execute · High pip_install_package Installing a package via pip executes an external process that downloads and installs code into the environment. Execute · High save_to_file_and_run The tool name strongly implies it writes content to a file and then executes it, combining Write and Execute actions.

4 of Python Code Runner's 4 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

FULL CATALOGUE

All 4 Python Code Runner tools

EXECUTE 4 tools

Execute run_python_code Run Python code in the current environment. Execute run_python_file Run an existing Python file. Execute pip_install_package Install a Python package using pip. Execute save_to_file_and_run save_to_file_and_run

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Python Code Runner

How many tools does the Python Code Runner MCP server expose? +

4 tools across 2 categories: Execute, Write. 0 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Python Code Runner? +

Register the Python Code Runner MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Python Code Runner tool call.

Deterministic rules across all 4 Python Code Runner tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PYTHON CODE RUNNER →

Free to start. No card required.

4 Python Code Runner tools catalogued and risk-classified — across an index of 43,000+ MCP servers.