AI agents call mobbin_search_screens 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 searches and retrieves design inspiration data from Mobbin's database. It performs a read-only query operation to find and filter screen designs. There are no side effects, data modifications, code execution, financial transactions, or destructive operations. The blast radius of misuse is minimal—an agent could only retrieve unwanted design data but cannot modify, delete, or execute operations.
From the tool's definition Tool name 'mobbin_search_screens' and description 'Search screens across all apps on Mobbin. Filter by screen patterns' indicates a retrieval/query operation with no modification or execution of external code.
Attacks that exploit this kind of access
Search screens across all apps on Mobbin. Filter by screen patterns (e.g.,. 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_search_screens: 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_search_screens 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_search_screens 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_search_screens. 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_search_screens 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 →