run_shell

Execute a shell command in the workspace directory. Use for running

SERVERGenkit MCP SOURCEgenkit-ai/genkit

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/firebase-genkit/run-shell.md

WHAT IT DOES

What run_shell does on Genkit MCP

AI agents invoke run_shell to trigger actions in Genkit 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 run_shell is rated High

Shell command execution is a classic Execute category action—it triggers external operations (shell processes) whose effects depend entirely on the arguments provided. A malicious or confused agent could run destructive commands (rm, dd, etc.), exfiltrate data, or compromise the system.

From the tool's definition Tool name 'run_shell' and description 'Execute a shell command in the workspace directory' explicitly indicates execution of arbitrary shell commands.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_shell safely

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

run_shell Rate-limited

run_shell 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_shell": {
      "limits": [
        {
          "counter": "run_shell_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 Genkit MCP, apply this rule, and every run_shell call is checked against it from then on.

FAQ

Questions about run_shell

What does the run_shell tool do? +

Execute a shell command in the workspace directory. Use for running. It is categorised as a Execute tool in the Genkit 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_shell? +

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

What risk level is run_shell? +

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

Can I rate-limit run_shell? +

Yes. Add a rate_limit block to the run_shell 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_shell completely? +

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

run_shell is provided by the Genkit MCP server (genkit-ai/genkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Genkit, and thousands of servers like it.

This server

All 72 Genkit tools → High-risk tools on this server →

Across the catalogue

run on 0sec →adb_shell_command on Android Forensics ADB MCP Server →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 →