Skip to content
Health

Calorie Calculator MCP tool in OpenAI Agents JS

Connect MultitaskAI to OpenAI Agents SDK agents in TypeScript as an MCPServerStreamableHttp server, then ask in plain words. OpenAI Agents JS calls Calorie Calculator with the right arguments and answers with the exact result.

Set up MultitaskAI MCP in OpenAI Agents JS

Add MultitaskAI to OpenAI Agents SDK agents in TypeScript as an MCPServerStreamableHttp server. It takes a minute and every tool comes with it.

  1. Create an API key in your MultitaskAI account.

  2. Create the server below with @openai/agents, with your key in place of YOUR_API_KEY.

  3. Add it to your agent's mcpServers and call connect() before running.

  4. Run the agent and check that it answers with MultitaskAI tools, then call close().

agent.ts
import { Agent, run, MCPServerStreamableHttp } from '@openai/agents';

const mcpServer = new MCPServerStreamableHttp({
  url: 'https://mcp.multitaskai.com',
  name: 'multitaskai',
  requestInit: {
    headers: { Authorization: 'Bearer YOUR_API_KEY' },
  },
});

const agent = new Agent({
  name: 'Assistant',
  instructions: 'Use the MultitaskAI tools to respond to user requests.',
  mcpServers: [mcpServer],
});

await mcpServer.connect();
const result = await run(agent, 'Which MultitaskAI tools can you use?');
console.log(result.finalOutput);
await mcpServer.close();

API key

OpenAI Agents JS sends your MultitaskAI API key in the Authorization header. Create a key in your account and use it in place of YOUR_API_KEY.

Read the OpenAI Agents JS guide

The full OpenAI Agents JS guide covers every step, the endpoint, signing in and how to check the connection.

Ask in plain words

Once MultitaskAI is connected, a request like this one is enough. OpenAI Agents JS picks Calorie Calculator, fills in the details and answers with the exact result.

  • No tool names or settings to learn
  • The same exact answer every time
  • Works in every client that speaks MCP
You

Calculate calories: 70, height (cm) 175, age 30 and gender "male".

Used Calorie Calculator
Basal Metabolic Rate (BMR)
1649 calories/day
Maintenance Calories (TDEE)
1979 calories/day
Lose Weight (slow)
1479 calories/day
Lose Weight (fast)
979 calories/day
Gain Weight (slow)
2479 calories/day
Gain Weight (fast)
2979 calories/day
Show the raw MCP call
tools/call request
{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "calorie-calculator",
        "arguments": {
            "value": 70,
            "height": 175,
            "age": 30,
            "gender": "male",
            "activity": "sedentary"
        }
    }
}
Result
Basal Metabolic Rate (BMR): 1649 calories/day

Maintenance Calories (TDEE): 1979 calories/day

---: ---

Lose Weight (slow): 1479 calories/day

Lose Weight (fast): 979 calories/day

Gain Weight (slow): 2479 calories/day

Gain Weight (fast): 2979 calories/day

More health MCP tools in OpenAI Agents JS

Free to start, unlimited with Pro

Every signed-in account gets 100 requests a day. MultitaskAI Pro removes the daily limit for €9 a month.

Free

For trying MultitaskAI and for light daily use.

€0forever

  • 100 requests a day
  • All 433 tools
  • OAuth connectors and API keys
  • Every request tied to your account

MultitaskAI Pro

Unlimited

For agents that work all day.

€9per month

  • Unlimited requests
  • All 433 tools
  • OAuth connectors and API keys
  • Billed monthly, cancel any time

Give your agent 433 tools in a minute

Sign in, add the endpoint to your client and ask. 100 requests a day are free.