AI agents call mobbin_quick_search 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.
The tool retrieves data (autocomplete suggestions and app metadata) without modifying, deleting, or executing anything. It is a pure read operation analogous to a search or lookup function. The low severity reflects that misuse would only expose design information from Mobbin's public database, which poses minimal risk.
From the tool's definition Tool description explicitly states it "Returns matching app IDs and names" and is used for "fast lookup before fetching full details." This is a query/search operation with no side effects.
Attacks that exploit this kind of access
Quick autocomplete search for apps by name. Returns matching app IDs and names. Use this for fast lookup before fetching full details. 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_quick_search: 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_quick_search 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_quick_search 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_quick_search. 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_quick_search 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 →