intent_start
Launch an Activity with a structured Android Intent. Supports action, component, data URI, category, typed extras, and activity flags. Android only; use intent_deeplink for iOS.
This record as markdown: /tools/alexgladkov-claude-in-mobile/intent-start.md
What intent_start does on Claude Mobile
AI agents invoke intent_start 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.
Why intent_start is rated High
This tool executes external operations on an Android device by launching Activities with developer-controlled Intent parameters. While not a direct shell command execution, launching arbitrary Activities with specified data and actions can trigger side effects that depend on the intent arguments provided.
From the tool's definition Tool description states it 'Launch[es] an Activity with a structured Android Intent' and supports various intent parameters including 'action, component, data URI, category, typed extras, and activity flags'.
Attacks that exploit this kind of access
The rule that runs intent_start 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 intent_start, this is the rule to start with:
intent_start 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every intent_start call is checked against it from then on.
Questions about intent_start
Launch an Activity with a structured Android Intent. Supports action, component, data URI, category, typed extras, and activity flags. Android only; use intent_deeplink for iOS. 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.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for intent_start: 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.
intent_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the intent_start 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 intent_start. 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.
intent_start 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.
More on Claude Mobile, and thousands of servers like it.
Across the catalogue