AI agents call search_recipes to retrieve information from Portals without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
top | integer | — | Maximum matches to return (default: 5). |
query | string | Yes | Search query, for example: keypad minimap puzzle |
category | string | — | Optional category filter, for example mechanics or scoring. |
includeContent | boolean | — | Include full recipe markdown content in each match (default: false). |
Parameters from the server's own tool schema.
This tool retrieves and filters data from a recipe manifest without creating, modifying, deleting, or executing anything. It is a simple read/search operation with minimal security risk. Confidence is high because the description is clear and unambiguous.
From the tool's definition Tool description states it 'Search[es] bundled recipe manifest entries by keywords, tags, and patterns' — a pure query operation with no modification or execution capability.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Search bundled recipe manifest entries by keywords, tags, and patterns. It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.
search_recipes accepts 4 parameters: top, query, category, includeContent. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Portals 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 Portals. 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 Portals MCP server (portals-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 →