AI agents call query_dps to retrieve information from DPSCoach without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the word 'Execute' in the description, the tool's actual function is querying (reading) data. The 'safe' qualifier and 'SELECT-only' constraint confirm it has no write, destructive, or side-effect capabilities. The severity is low because read-only queries against a game analytics database pose minimal risk; even if misused, no data is modified or lost.
From the tool's definition Tool description states 'Execute a safe SELECT-only query' — explicitly limited to SELECT operations with no modification or deletion capabilities.
Attacks that exploit this kind of access
Execute a safe SELECT-only query against the in-memory events table. It is categorised as a Read tool in the DPSCoach MCP Server, which means it retrieves data without modifying state.
Register the DPSCoach MCP server in PolicyLayer and add a rule for query_dps: 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 DPSCoach. Nothing to install.
query_dps 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 query_dps 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 query_dps. 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.
query_dps is provided by the DPSCoach MCP server (stalcup-dev/tl-dps-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 →