AI agents call list_avds to retrieve information from Espresso without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool merely enumerates existing AVDs on the system. It has no side effects, does not execute code or commands, and does not modify any data. This is a straightforward information retrieval operation, placing it clearly in the Read category with low severity since listing AVDs poses minimal risk even if accessed by an untrusted agent.
From the tool's definition Tool name is 'list_avds' and description states 'List all available Android Virtual Devices (AVDs)' — this is a query operation that retrieves information without modifying or executing anything.
Attacks that exploit this kind of access
List all available Android Virtual Devices (AVDs). It is categorised as a Read tool in the Espresso MCP Server, which means it retrieves data without modifying state.
Register the Espresso MCP server in PolicyLayer and add a rule for list_avds: 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 Espresso. Nothing to install.
list_avds 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 list_avds 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 list_avds. 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.
list_avds is provided by the Espresso MCP server (vs4vijay/espresso-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 →