How to Use the Spoonacular MCP in Mastra AI

Q: Which types of recipes does Spoonacular Alternative support in Mastra AI?

The server supports general searching via searchrecipes, and also provides specific meal planning data using getrecipeinstructions. You can make the instruction delivery part of a critical, reliable step.

Build fault-tolerant food data pipelines with Mastra AI's workflow engine.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Spoonacular MCP to Mastra AI

Create your Vinkius account to connect Spoonacular to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Spoonacular with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Reliably search and analyze recipes.

You can build complex workflows that chain calls. For example, if a primary call to `search_recipes` fails due to rate limiting, Mastra automatically retries the request using exponential backoff. This ensures your workflow doesn't just fail; it gets back on track.

Integrate recipe data from web sources reliably.

Using `extract_recipe` within a multi-step process is powerful. You can set up conditional logic: if the URL extraction fails, Mastra can automatically prompt an admin notification instead of crashing the workflow. This makes your pipelines resilient.

Handle complex nutritional planning workflows.

Set up a full meal plan that requires multiple checks. First, run `recipes_by_ingredients`. Then, check the results against dietary needs using `get_recipe_nutrition`. Mastra's workflow engine ensures that if any step fails, it notifies you before consuming resources.

Setup guide

Set up Spoonacular MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Spoonacular tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "spoonacular-alternative-mcp-client",
  servers: {
    "spoonacular-alternative-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Spoonacular Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Spoonacular tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Spoonacular transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Spoonacular. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Spoonacular now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Spoonacular MCP in Mastra AI

You map the MCP Server into a multi-step workflow. You don't just execute tools; you define the logic: 'If step A succeeds, run B; otherwise, notify and stop.' This gives predictable behavior.

Yes. You can build a conditional branch that checks user preference (e.g., 'must be low carb'). If the result of `recipes_by_nutrients` doesn't meet criteria, your workflow automatically switches to suggesting alternative search parameters.

You can. Define a loop in your workflow that takes a list of IDs and repeatedly calls `get_recipes_bulk`. If the connection drops midway, Mastra's built-in retries ensure you pick up exactly where you left off.

The server supports general searching via `search_recipes`, and also provides specific meal planning data using `get_recipe_instructions`. You can make the instruction delivery part of a critical, reliable step.

The server touches Recipe IDs and Nutritional Data. Because Mastra handles state, you can guarantee that every piece of nutritional data—from the total serving size to individual nutrient counts—is processed completely before moving on.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript