system_run_python

A execute tool on the Container- MCP server.

SERVERContainer-MCP SOURCE54rt1n/container-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/54rt1n-container-mcp/system-run-python.md

WHAT IT DOES

What system_run_python does on Container-MCP

AI agents invoke system_run_python to trigger actions in Container-MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why system_run_python is rated High

Executing Python code is an Execute-category action with critical severity due to the broad attack surface: arbitrary code execution can read/write files, make network calls, modify system state, or escape the sandbox. Even in a sandboxed container, misuse by a compromised or adversarial AI agent poses severe risk.

From the tool's definition Tool name 'system_run_python' indicates execution of Python code; combined with server description stating it provides 'sandboxed environments for AI systems to safely execute code,' this tool runs arbitrary Python in a container.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs system_run_python safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Container-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For system_run_python, this is the rule to start with:

system_run_python Rate-limited

system_run_python stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "system_run_python": {
      "limits": [
        {
          "counter": "system_run_python_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Container-MCP, apply this rule, and every system_run_python call is checked against it from then on.

FAQ

Questions about system_run_python

What does the system_run_python tool do? +

system_run_python is a execute tool on the Container MCP server. It is categorised as a Execute tool in the Container-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on system_run_python? +

Register the Container MCP server in PolicyLayer and add a rule for system_run_python: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Container-MCP. Nothing to install.

What risk level is system_run_python? +

system_run_python is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit system_run_python? +

Yes. Add a rate_limit block to the system_run_python rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block system_run_python completely? +

Set action: deny in the PolicyLayer policy for system_run_python. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides system_run_python? +

system_run_python is provided by the Container MCP server (54rt1n/container-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Container, and thousands of servers like it.

This server

All 27 Container tools → High-risk tools on this server →

Across the catalogue

editor_run_template on 010 Editor →run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →