grant_permissions · AVD MCP Server MCP: Risk & Policy

WHAT IT DOES

What grant_permissions does on AVD MCP Server

AI agents invoke grant_permissions to trigger actions in AVD MCP Server. 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 grant_permissions needs a policy

This tool executes the Android 'pm grant' command, which modifies the runtime permission state of applications on the emulator. While not destructive (permissions can be revoked), it triggers external operations (permission grants) whose effects depend on which permissions are granted to which apps.

From the tool's definition The tool uses 'pm grant' (Android Package Manager grant command) to concede/grant permissions. The description states it grants permissions and returns per permission, indicating execution of permission-granting commands on the Android Virtual Device.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

grant_permissions Rate-limited

grant_permissions 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": {
    "grant_permissions": {
      "limits": [
        {
          "counter": "grant_permissions_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 AVD MCP Server, so you can run agents against it safely.

FAQ

Questions about grant_permissions

What does the grant_permissions tool do? +

Concede permissões com pm grant e retorno por permissão. It is categorised as a Execute tool in the AVD MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on grant_permissions? +

Register the AVD MCP Server MCP server in PolicyLayer and add a rule for grant_permissions: 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 AVD MCP Server. Nothing to install.

What risk level is grant_permissions? +

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

Can I rate-limit grant_permissions? +

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

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

grant_permissions is provided by the AVD MCP Server MCP server (jramalho/avd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.