AI agents call queue.stats to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves queue depth metrics scoped to a specific wallet. It performs a data query with no side effects, reversible actions, code execution, destructive operations, or financial transactions. The read-only nature of statistics collection places it squarely in the Read category with low severity—misuse would only expose queue status information without operational harm.
From the tool's definition Tool name 'queue.stats' and description 'depth of a queue, scoped to YOUR wallet - counts of...' indicates a statistics/query operation that retrieves queue depth information.
Attacks that exploit this kind of access
QUEUE: depth of a queue, scoped to YOUR wallet - counts of. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for queue.stats: 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 Mcp. Nothing to install.
queue.stats 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 queue.stats 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 queue.stats. 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.
queue.stats is provided by the MCP server (@2sio/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 →