How to Use the API Ninjas MCP in AutoGen

Q: How do AutoGen agents share API Ninjas tool outputs?

When an agent calls a tool like getnutrition, the resulting JSON is posted to the group chat. All other agents in the AutoGen conversation can read this payload and use it to adjust their recommendations.

Q: How do I register the API Ninjas MCP Server tools with AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP transport URL. Pass the resulting tool list directly to your AssistantAgent constructor.

Q: How does AutoGen handle errors from the fitness tools?

If getbodyfat returns an error due to invalid measurements, the execution agent shares the error with the group. A coordinator agent then asks the user for corrected measurements.

Let AutoGen agents debate workout routines and diet plans using live API Ninjas metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect API Ninjas MCP to AutoGen

Create your Vinkius account to connect API Ninjas to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup API Ninjas with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve diet and exercise conflicts via AutoGen debates

The `get_tdee` and `get_nutrition` tools provide the exact caloric numbers your AutoGen agents need to negotiate meal plans. One agent can act as a strict nutrition coach while another acts as a performance coach, debating the optimal macro split. They use real-time data from the API Ninjas server to back up their arguments. By connecting to this MCP server, they can negotiate and verify that the proposed meal plan aligns with the user's calculated energy expenditure.

Let agents collaborate on workout design

The `get_exercises` tool delivers step-by-step workout guides that your AutoGen agents analyze from different angles. A safety agent can review the equipment and difficulty level of an exercise, while a training agent argues for its muscle-building benefits. This multi-agent setup ensures your users get balanced routines. The agents query the API Ninjas server, debate the safety of intermediate or expert movements, and only present the routine once they reach a consensus.

Validate body metrics across AutoGen agents

The `get_body_fat` and `get_bmr` tools allow your agents to cross-verify physical data before saving it. An auditor agent can check if the waist and neck measurements passed to the body fat calculator make physical sense before allowing the main agent to run the calculation. This prevents garbage data from corrupting your tracking logs. By exposing this MCP Server to your AutoGen group, you ensure every biometric input is analyzed and validated by specialized agents.

Setup guide

Set up API Ninjas MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes API Ninjas tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="API Ninjas_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent API Ninjas data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="API Ninjas_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent API Ninjas data")
    print(result.messages[-1].content)

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 API Ninjas. 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 API Ninjas 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 API Ninjas MCP in AutoGen

When an agent calls a tool like `get_nutrition`, the resulting JSON is posted to the group chat. All other agents in the AutoGen conversation can read this payload and use it to adjust their recommendations.

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP transport URL. Pass the resulting tool list directly to your `AssistantAgent` constructor.

Yes, you can assign different tools to different agents. For example, give your fitness agent access to `get_tdee` and your meal planner agent access to `get_nutrition` to enforce strict division of labor.

If `get_body_fat` returns an error due to invalid measurements, the execution agent shares the error with the group. A coordinator agent then asks the user for corrected measurements.

Yes, because Vinkius runs the MCP tools inside ephemeral, zero-trust sandboxes. Your raw body measurements are never cached on the server, and the agent-to-agent communication remains local to your secure environment.

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