permission_grant

Grant app permission (Android runtime / iOS privacy)

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

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/alexgladkov-claude-in-mobile/permission-grant.md

WHAT IT DOES

What permission_grant does on Claude Mobile

AI agents invoke permission_grant to trigger actions in Claude Mobile. 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 permission_grant is rated High

Granting permissions to apps on Android or iOS modifies security settings and access controls for the device. This is an Execute-level action that triggers external OS-level operations with real security implications — it can enable apps to access sensitive resources (camera, microphone, location, contacts, etc.).

From the tool's definition Grant app permission (Android runtime / iOS privacy)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs permission_grant safely

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

permission_grant Rate-limited

permission_grant 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": {
    "permission_grant": {
      "limits": [
        {
          "counter": "permission_grant_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 Claude Mobile, apply this rule, and every permission_grant call is checked against it from then on.

FAQ

Questions about permission_grant

What does the permission_grant tool do? +

Grant app permission (Android runtime / iOS privacy). It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on permission_grant? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for permission_grant: 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 Claude Mobile. Nothing to install.

What risk level is permission_grant? +

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

Can I rate-limit permission_grant? +

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

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

permission_grant is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →