Queries the
AI agents call query_comments 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 or searches comment data from the MongoDB database without modifying, deleting, or executing arbitrary operations. Even if it queries across a large dataset, the blast radius of misuse is limited to data exposure rather than modification or destruction. The incomplete description lowers confidence slightly, but the 'query' prefix and server context strongly indicate read-only behavior.
From the tool's definition Tool name 'query_comments' and prefix 'query' indicate data retrieval. Description incomplete ('Queries the') but context shows this server manages MongoDB queries for recipes, comments, users, and utensils.
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_comments: 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_comments 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_comments 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_comments. 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_comments 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 →