AI agents call filter_recipes_by_time to retrieve information from Paprika without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing recipe data based on time parameters. It performs a query operation with no side effects, no data modification, and no irreversible actions. It is purely informational/read-only.
From the tool's definition Tool name contains 'filter' and description states 'Filter recipes by time constraints' with no mention of modifications, deletions, or side effects. It queries/retrieves data based on parameters.
Attacks that exploit this kind of access
Filter recipes by time constraints (prep time, cook time, or total time). It is categorised as a Read tool in the Paprika MCP Server, which means it retrieves data without modifying state.
Register the Paprika MCP server in PolicyLayer and add a rule for filter_recipes_by_time: 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 Paprika. Nothing to install.
filter_recipes_by_time 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 filter_recipes_by_time 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 filter_recipes_by_time. 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.
filter_recipes_by_time is provided by the Paprika MCP server (sandordaroczi/paprika-mcp-python-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 →