run_python · Docsmith MCP: Risk & Policy

WHAT IT DOES

What run_python does on Docsmith MCP

AI agents invoke run_python to trigger actions in Docsmith 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.

WHY IT NEEDS A POLICY

Why run_python needs a policy

This tool allows arbitrary Python code execution with no apparent constraints on what code can be run. The ability to execute custom Python with access to 'any file format' and 'Python libraries' creates extreme risk: an AI agent could delete files, exfiltrate data, modify documents, or perform unauthorized operations.

From the tool's definition "Execute Python code for flexible file operations, data processing, and custom tasks. Supports any file format and Python libraries." Combined with sibling tools (read_document, write_document, get_document_info), this tool enables arbitrary code execution…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_python Rate-limited

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": {
    "run_python": {
      "limits": [
        {
          "counter": "run_python_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Docsmith MCP, so you can run agents against it safely.

FAQ

Questions about run_python

What does the run_python tool do? +

Execute Python code for flexible file operations, data processing, and custom tasks. Supports any file format and Python libraries. It is categorised as a Execute tool in the Docsmith 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 run_python? +

Register the Docsmith MCP server in PolicyLayer and add a rule for 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 Docsmith MCP. Nothing to install.

What risk level is run_python? +

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

Can I rate-limit run_python? +

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

Set action: deny in the PolicyLayer policy for 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 run_python? +

run_python is provided by the Docsmith MCP server (mcpc-tech/docsmith-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.