API Ninjas MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect API Ninjas through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="API Ninjas Assistant",
instructions=(
"You help users interact with API Ninjas. "
"You have access to 8 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from API Ninjas"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About API Ninjas MCP Server
Connect to API Ninjas and access a comprehensive suite of health and fitness tools through natural conversation.
The OpenAI Agents SDK auto-discovers all 8 tools from API Ninjas through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries API Ninjas, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Exercise Search — Search 1000+ exercises by name, type, muscle group and difficulty with step-by-step instructions
- Calories Burned — Calculate calories burned for various activities based on weight and duration
- Body Fat — Estimate body fat percentage using the US Navy method
- BMR & TDEE — Calculate Basal Metabolic Rate and Total Daily Energy Expenditure
- Nutrition — Get nutritional info for any food item (calories, protein, carbs, fat)
- Sleep — Get recommended sleep duration based on age and gender
- Steps — Calculate calories burned and distance from step count
The API Ninjas MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect API Ninjas to OpenAI Agents SDK via MCP
Follow these steps to integrate the API Ninjas MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 8 tools from API Ninjas
Why Use OpenAI Agents SDK with the API Ninjas MCP Server
OpenAI Agents SDK provides unique advantages when paired with API Ninjas through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
API Ninjas + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the API Ninjas MCP Server delivers measurable value.
Automated workflows: build agents that query API Ninjas, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries API Ninjas, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through API Ninjas tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query API Ninjas to resolve tickets, look up records, and update statuses without human intervention
API Ninjas MCP Tools for OpenAI Agents SDK (8)
These 8 tools become available when you connect API Ninjas to OpenAI Agents SDK via MCP:
get_bmr
Requires weight (kg), height (cm), age and gender. Returns BMR value in calories/day. Calculate Basal Metabolic Rate
get_body_fat
Requires waist, neck and height measurements (in cm). For women, also requires hip measurement. Returns body fat percentage and category (lean, fitness, acceptable, obese). Estimate body fat percentage
get_calories_burned
Requires activity name, weight (kg) and duration (minutes). Returns activity name, duration, calories burned and MET value. Calculate calories burned for an activity
get_exercises
Supports filtering by name, type (cardio, olympic_weightlifting, plyometrics, powerlifting, strength, stretching, strongman), muscle (abdominals, abductors, adductors, biceps, calves, chest, forearms, glutes, hamstrings, lats, lower_back, middle_back, neck, quadriceps, traps, triceps) and difficulty (beginner, intermediate, expert). Returns exercise name, type, muscle worked, equipment needed, difficulty level and step-by-step instructions. Search exercises by name, type, muscle or difficulty
get_nutrition
Returns calories, protein, carbohydrates, fat, saturated fat, cholesterol, sodium, potassium, fiber and sugar per 100g serving. Get nutrition info for a food item
get_sleep
Returns recommended sleep range and whether current sleep is adequate. Get recommended sleep duration
get_steps
Requires step count and optionally weight (kg), height (cm), age and gender for more accurate calculations. Calculate calories and distance from steps
get_tdee
Requires weight (kg), height (cm), age, gender and activity level. Returns TDEE value in calories/day with breakdown by activity level. Calculate Total Daily Energy Expenditure
Example Prompts for API Ninjas in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with API Ninjas immediately.
"Find chest exercises for beginners."
"What's the nutritional info for a banana?"
"Calculate my BMR. I'm 30 years old, male, 80kg, 180cm."
Troubleshooting API Ninjas MCP Server with OpenAI Agents SDK
Common issues when connecting API Ninjas to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
API Ninjas + OpenAI Agents SDK FAQ
Common questions about integrating API Ninjas MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect API Ninjas with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect API Ninjas to OpenAI Agents SDK
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.