AI agents call queue_status to retrieve information from Teammate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about queues and recent completions. It has no side effects, does not modify state, and merely exposes metrics for observability. It falls squarely into the Read category with low severity because the blast radius of misuse is minimal—an agent querying queue status cannot cause harm.
From the tool's definition Tool description explicitly states it returns "queue counts + recent completions (debugging)". The verb "return" indicates data retrieval with no modification, creation, or deletion of data. It is expressly labeled as a debugging utility.
Attacks that exploit this kind of access
Return queue counts + recent completions (debugging). It is categorised as a Read tool in the Teammate MCP Server, which means it retrieves data without modifying state.
Register the Teammate MCP server in PolicyLayer and add a rule for queue_status: 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 Teammate. Nothing to install.
queue_status 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_status 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_status. 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_status is provided by the Teammate MCP server (jonghklee/teammate-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 →