query_monthly_sales
AI agents call query_monthly_sales to retrieve information from Sales MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve monthly sales data without modifying it. While the description is empty, the name and server context indicate a query operation (Read category). Severity is low because querying sales data has no destructive or financial transaction effects—it gathers information for analysis.
From the tool's definition Tool name 'query_monthly_sales' indicates querying/retrieval of sales data. Server description states it 'query[ies] enterprise sales data from a local SQLite database' with 'human-in-the-loop review buttons', suggesting read-only data access rather than…
Attacks that exploit this kind of access
query_monthly_sales. It is categorised as a Read tool in the Sales MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sales MCP Server MCP server in PolicyLayer and add a rule for query_monthly_sales: 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 Sales MCP Server. Nothing to install.
query_monthly_sales 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_monthly_sales 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_monthly_sales. 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_monthly_sales is provided by the Sales MCP Server MCP server (pessini/langgraph-mcp-prefab-ui). 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 →