# run_shell

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

Agent View of the PolicyLayer registry record for `run_shell`. HTML page: https://policylayer.com/tools/firebase-genkit/run-shell

## Facts

- Tool: `run_shell`
- Server: Genkit MCP (`genkit-ai/genkit`) — https://policylayer.com/tools/firebase-genkit.md
- Homepage: https://github.com/genkit-ai/genkit
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run_shell",
    "arguments": {}
  }
}
```

## 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 own definition: "Tool name 'run_shell' and description 'Execute a shell command in the workspace directory' explicitly indicates execution of arbitrary shell commands."

## Use case

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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Genkit MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_shell": {
      "limits": [
        {
          "counter": "run_shell_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Genkit MCP (71)

- `removeTask` — Destructive — https://policylayer.com/tools/firebase-genkit/removetask.md
- `characterGenerator` — Execute — https://policylayer.com/tools/firebase-genkit/charactergenerator.md
- `delegate_to_coder` — Execute — https://policylayer.com/tools/firebase-genkit/delegate-to-coder.md
- `delegate_to_researcher` — Execute — https://policylayer.com/tools/firebase-genkit/delegate-to-researcher.md
- `run_flow` — Execute — https://policylayer.com/tools/firebase-genkit/run-flow.md
- `screenshot` — Execute — https://policylayer.com/tools/firebase-genkit/screenshot.md
- `slowWork` — Execute — https://policylayer.com/tools/firebase-genkit/slowwork.md
- `start_runtime` — Execute — https://policylayer.com/tools/firebase-genkit/start-runtime.md
- `transferToAgent` — Execute — https://policylayer.com/tools/firebase-genkit/transfertoagent.md
- `use_skill` — Execute — https://policylayer.com/tools/firebase-genkit/use-skill.md
- `processPayment` — Financial — https://policylayer.com/tools/firebase-genkit/processpayment.md
- `request_transfer` — Financial — https://policylayer.com/tools/firebase-genkit/request-transfer.md
- `reservationTool` — Financial — https://policylayer.com/tools/firebase-genkit/reservationtool.md
- `transferMoney` — Financial — https://policylayer.com/tools/firebase-genkit/transfermoney.md
- `add` — Other — https://policylayer.com/tools/firebase-genkit/add.md
- `askQuestion` — Other — https://policylayer.com/tools/firebase-genkit/askquestion.md
- `datePicker` — Other — https://policylayer.com/tools/firebase-genkit/datepicker.md
- `error_tool` — Other — https://policylayer.com/tools/firebase-genkit/error-tool.md
- `exitTool` — Other — https://policylayer.com/tools/firebase-genkit/exittool.md
- `gablorken` — Other — https://policylayer.com/tools/firebase-genkit/gablorken.md
- `test_http` — Other — https://policylayer.com/tools/firebase-genkit/test-http.md
- `account_record` — Read — https://policylayer.com/tools/firebase-genkit/account-record.md
- `ask_user` — Read — https://policylayer.com/tools/firebase-genkit/ask-user.md
- `celsiusToFahrenheit` — Read — https://policylayer.com/tools/firebase-genkit/celsiustofahrenheit.md
- `confirmBooking` — Read — https://policylayer.com/tools/firebase-genkit/confirmbooking.md
- `current_weather` — Read — https://policylayer.com/tools/firebase-genkit/current-weather.md
- `dailySpecial` — Read — https://policylayer.com/tools/firebase-genkit/dailyspecial.md
- `dynamicGablorkenTool` — Read — https://policylayer.com/tools/firebase-genkit/dynamicgablorkentool.md
- `echo_meta_tool` — Read — https://policylayer.com/tools/firebase-genkit/echo-meta-tool.md
- `fetchCatalog` — Read — https://policylayer.com/tools/firebase-genkit/fetchcatalog.md
- …and 41 more: https://policylayer.com/tools/firebase-genkit.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=firebase-genkit · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/firebase-genkit