getRecipes

Get a list of recipes for a given recipe name or ingredient(s). Returns a list of recipes with nutrition information when available. To access more results, use the limit parameter to limit the number of results and the offset parameter to offset results for pagination in multiple API calls.

SERVERAPI Ninjas SOURCEhttps://mcp.api-ninjas.com/mcp

Low RISK CLASS

Category Read

Parameters 40 required

Recommended Allowedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/com-api-ninjas-mcp/getrecipes.md

WHAT IT DOES

What getRecipes does on API Ninjas

AI agents call getRecipes to retrieve information from API Ninjas without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`limit`	integer	—	Number of results to return. Must be between 1 and 10. If not set, a default value of 1 will be used. Premium subscribers only.
`title`	string	—	Recipe title to search for.
`offset`	integer	—	Number of results to offset for pagination. Premium subscribers only.
`ingredients`	string	—	Comma-separated list of ingredients to search for. Premium subscribers only.

Parameters from the server's own tool schema.

RISK

Why getRecipes is rated Low

Even though getRecipes only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs getRecipes safely

PolicyLayer is an MCP gateway: it sits between your AI agents and API Ninjas, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For getRecipes, this is the rule to start with:

getRecipes Allowed

getRecipes is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "getRecipes": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect API Ninjas, apply this rule, and every getRecipes call is checked against it from then on.

FAQ

Questions about getRecipes

What does the getRecipes tool do? +

What parameters does getRecipes accept? +

getRecipes accepts 4 parameters: limit, title, offset, ingredients. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on getRecipes? +

Register the API Ninjas MCP server in PolicyLayer and add a rule for getRecipes: 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 API Ninjas. Nothing to install.

What risk level is getRecipes? +

getRecipes is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit getRecipes? +

Yes. Add a rate_limit block to the getRecipes 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.

How do I block getRecipes completely? +

Set action: deny in the PolicyLayer policy for getRecipes. 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.

What MCP server provides getRecipes? +

getRecipes is provided by the API Ninjas MCP server (https://mcp.api-ninjas.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on API Ninjas, and thousands of servers like it.

This server

All 244 API Ninjas tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →