AI agents use grant-permission to create or update resources in ADB MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ADB MCP Server environment.
Granting permissions to an app modifies the security configuration of the Android system reversibly (permissions can be revoked). However, the blast radius is high because an AI agent could grant sensitive permissions (e.g., READ_CONTACTS, CAMERA, ACCESS_FINE_LOCATION, or even INSTALL_PACKAGES) to malicious or unintended apps, potentially enabling further privilege escalation or data exfiltration.
From the tool's definition Grant a specific permission to an app
Documented attack patterns abuse exactly the kind of access grant-permission gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ADB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for grant-permission:
{
"version": "1",
"default": "deny",
"tools": {
"grant-permission": {
"limits": [
{
"counter": "grant-permission_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}grant-permission stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Grant a specific permission to an app. It is categorised as a Write tool in the ADB MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for grant-permission: 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 ADB MCP Server. Nothing to install.
grant-permission is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the grant-permission 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.
Set action: deny in the PolicyLayer policy for grant-permission. 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.
grant-permission is provided by the ADB MCP Server MCP server (jiantao88/android-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ADB MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 ADB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.