AI agents call get_database_stats to retrieve information from Fichapao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves summary statistics about bakery recipes organized by status and pending items. It performs a read-only query that returns no side effects—no data is created, modified, or deleted. The operation is purely informational, making it a Read category tool with low severity since misuse would only expose non-sensitive aggregate metadata about recipe status.
From the tool's definition Tool name 'get_database_stats' and description 'Retorna um resumo da base de fichas tecnicas por status e pendencias' (Returns a summary of the technical sheets database by status and pending items) indicate a retrieval operation that queries aggregate…
Attacks that exploit this kind of access
Retorna um resumo da base de fichas tecnicas por status e pendencias. It is categorised as a Read tool in the Fichapao MCP Server, which means it retrieves data without modifying state.
Register the Fichapao MCP server in PolicyLayer and add a rule for get_database_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 Fichapao. Nothing to install.
get_database_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 get_database_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 get_database_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.
get_database_stats is provided by the Fichapao MCP server (kratos4ai/fichapao-mcp-server). 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 →