Search your recipe collection by name, cuisine, or ingredient — with optional must-have / exclude ingredient filters. Returns the full recipe.
AI agents call search_recipes to retrieve information from Personal Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries a recipe database and returns matching results. It performs semantic search and filtering but has no side effects, cannot modify or delete recipes, and cannot execute external code or commands. The only data returned is recipe information the user already owns. Blast radius is negligible even if an AI agent misuses it—it only exposes the user's own recipe data.
From the tool's definition Tool description states 'Search your recipe collection' and 'Returns the full recipe' — retrieves data with no modification, deletion, or execution. Search and retrieval are quintessential Read operations.
Attacks that exploit this kind of access
Search your recipe collection by name, cuisine, or ingredient — with optional must-have / exclude ingredient filters. Returns the full recipe. It is categorised as a Read tool in the Personal Brain MCP Server, which means it retrieves data without modifying state.
Register the Personal Brain MCP server in PolicyLayer and add a rule for search_recipes: 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 Personal Brain. Nothing to install.
search_recipes 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 search_recipes 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 search_recipes. 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.
search_recipes is provided by the Personal Brain MCP server (phantomts/personal-brain-mcp). 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 →