run_in_venv

THE RISK

High Risk

Why run_in_venv needs a policy

This tool executes arbitrary commands within a Python virtual environment. The effects are entirely dependent on what command is passed as an argument—it could modify files, install packages, call external APIs, or perform any shell operation.

From the tool's definition Tool name 'run_in_venv' and description 'Run a command in virtual environment' directly indicate execution of arbitrary commands with side effects that depend on the command argument.

Documented attack patterns abuse exactly the kind of access run_in_venv gives an agent:

POLICY

How to control run_in_venv

PolicyLayer is an MCP gateway — it sits between your AI agents and Venv, and nothing reaches the server without passing your rules. This is the rule we recommend for run_in_venv:

policy.json

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

run_in_venv 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.

Create a free account and register Venv — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Venv tools

Destructive remove_package Remove package from pyproject.toml file and update the virtual environment. Returns True i Write add_package Add package to pyproject.toml and update the virtual environment. Returns True if successf Write add_packages Add many packages to pyproject.toml at once and update the virtual environment. Write init Initialize virtual environment. Returns True if successful. Write sync Sync pyproject.toml with virtual environment. Returns True if successful.

All 6 Venv tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Venv → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_in_venv

What does the run_in_venv tool do? +

Run a command in virtual environment. Returns True if successful. It is categorised as a Execute tool in the Venv MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_in_venv? +

Register the Venv MCP server in PolicyLayer and add a rule for run_in_venv: 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 Venv. Nothing to install.

What risk level is run_in_venv? +

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

Can I rate-limit run_in_venv? +

Yes. Add a rate_limit block to the run_in_venv 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 run_in_venv completely? +

Set action: deny in the PolicyLayer policy for run_in_venv. 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 run_in_venv? +

run_in_venv is provided by the Venv MCP server (sparfenyuk/venv-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Venv tool call.

Start from Venv, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →