Queries the
AI agents call query_users to retrieve information from Recettes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user data from the MongoDB database without modifying, deleting, or executing operations. It is a Read operation. Severity is medium rather than low because querying user data could expose personally identifiable information (PII) or user details that an AI agent should not access without proper authorization, creating privacy and security risks.
From the tool's definition Tool name 'query_users' and context indicating it 'Queries' a MongoDB database of users, comments, users, and utensils. The description is incomplete ('Queries the') but the intent to retrieve user data is clear.
Attacks that exploit this kind of access
Queries the. It is categorised as a Read tool in the Recettes MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Recettes MCP Server MCP server in PolicyLayer and add a rule for query_users: 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 Recettes MCP Server. Nothing to install.
query_users 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_users 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_users. 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_users is provided by the Recettes MCP Server MCP server (symfomany/mcp-tuto). 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 →