shell_run · Universal Dev MCP: Risk & Policy

WHAT IT DOES

What shell_run does on Universal Dev MCP

AI agents invoke shell_run to trigger actions in Universal Dev 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 shell_run needs a policy

Shell command execution is a quintessential Execute category risk: it can trigger external operations, install packages, modify system state, exfiltrate data, or destroy infrastructure depending on arguments.

From the tool's definition Tool name is 'shell_run' and description states it runs 'koi bhi terminal command' (any terminal command) in the project directory. This permits arbitrary shell command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_run Rate-limited

shell_run 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": {
    "shell_run": {
      "limits": [
        {
          "counter": "shell_run_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 Universal Dev MCP, so you can run agents against it safely.

FAQ

Questions about shell_run

What does the shell_run tool do? +

Koi bhi terminal command chalao project directory mein. It is categorised as a Execute tool in the Universal Dev 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 shell_run? +

Register the Universal Dev MCP server in PolicyLayer and add a rule for shell_run: 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 Universal Dev MCP. Nothing to install.

What risk level is shell_run? +

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

Can I rate-limit shell_run? +

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

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

shell_run is provided by the Universal Dev MCP server (kallusuvaidyam/universal_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.