AI agents call mobbin_get_app_flows to retrieve information from Mobbin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries design flow data from the Mobbin database without creating, modifying, deleting, or executing anything. It is a read-only operation with no side effects. The blast radius of misuse is minimal—an attacker could only enumerate design flows, which are publicly available reference materials, with no ability to alter or access sensitive systems.
From the tool's definition Tool description states 'Get all user flows for a specific app on Mobbin' and 'Returns each flow'. The verb 'Get' and absence of any modification language (create, update, delete, execute) indicate pure data retrieval.
Attacks that exploit this kind of access
Get all user flows for a specific app on Mobbin. Pair with mobbin_quick_search: quick_search -> app_id -> get_app_flows. Returns each flow. It is categorised as a Read tool in the Mobbin MCP Server, which means it retrieves data without modifying state.
Register the Mobbin MCP server in PolicyLayer and add a rule for mobbin_get_app_flows: 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 Mobbin. Nothing to install.
mobbin_get_app_flows is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mobbin_get_app_flows 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 mobbin_get_app_flows. 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.
mobbin_get_app_flows is provided by the Mobbin MCP server (mobbin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →