Check for pending user requests submitted via the browser UI. Drains the queue.
AI agents call check_requests to retrieve information from Claude DJ MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves pending requests from a queue. While it drains the queue (removing items from the queue's perspective), this is a standard read operation that empties a transient message buffer rather than destructively deleting persistent data. The operation is reversible in practice (new requests can be submitted) and produces no side effects beyond consuming already-submitted requests.
From the tool's definition Tool description states it 'Check[s] for pending user requests' and 'Drains the queue' — retrieval operations with no modifications to underlying data structures or external state.
Attacks that exploit this kind of access
Check for pending user requests submitted via the browser UI. Drains the queue. It is categorised as a Read tool in the Claude DJ MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude DJ MCP server in PolicyLayer and add a rule for check_requests: 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 Claude DJ MCP. Nothing to install.
check_requests 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 check_requests 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 check_requests. 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.
check_requests is provided by the Claude DJ MCP server (uetuluk/claude-dj-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 →