How to Use the API Ninjas MCP in CrewAI

Q: How do I connect the API Ninjas MCP Server to a CrewAI agent?

Pass your Vinkius server URL directly into the agent's mcps list parameter. CrewAI handles the connection and exposes tools like getnutrition to that specific agent.

Q: Can I restrict which API Ninjas MCP Server tools are exposed to a CrewAI agent?

Yes. Use MCPServerHTTP with a toolfilter to only expose specific tools. You can give your Trainer agent access to getexercises while blocking it from getnutrition.

Run autonomous teams of fitness, nutrition, and exercise agents using CrewAI and the API Ninjas MCP Server.

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 CrewAI

Create your Vinkius account to connect API Ninjas to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run specialized health crews with CrewAI

The `get_nutrition` and `get_exercises` tools can be assigned to different specialized agents in your crew. You can have a Nutritionist Agent analyze meals while a Trainer Agent designs the workout routine. These agents collaborate in sequence, sharing memory of what the user ate and what exercises they need. The final output is a cohesive plan built by autonomous experts.

Calculate metabolic balance with cooperating agents

The `get_bmr` and `get_tdee` tools allow your crew to audit energy balances. One agent calculates the baseline metabolism while another adjusts for daily step counts using the `get_steps` tool. This multi-agent setup prevents single-agent confusion. Each agent focuses on one metric, passing structured data to the next teammate in the chain.

Build an autonomous sleep and recovery monitor

The `get_sleep` and `get_body_fat` tools help your crew evaluate recovery metrics via MCP. A supervisor agent can analyze sleep adequacy and trigger a body composition review if recovery targets are missed. You set up these rules using standard python scripts. The crew runs headless in your CI/CD pipeline or terminal, executing assessments without human intervention.

Setup guide

Set up API Ninjas MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke API Ninjas tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="API Ninjas Analyst",
    goal="Access and analyze API Ninjas data via MCP.",
    backstory="Expert analyst with direct API Ninjas access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent API Ninjas transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="API Ninjas Analyst",
        goal="Access and analyze API Ninjas data via MCP.",
        backstory="Expert analyst with direct API Ninjas access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent API Ninjas transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius server URL directly into the agent's `mcps` list parameter. CrewAI handles the connection and exposes tools like `get_nutrition` to that specific agent.

Yes. Use `MCPServerHTTP` with a `tool_filter` to only expose specific tools. You can give your Trainer agent access to `get_exercises` while blocking it from `get_nutrition`.

CrewAI uses shared memory. When your Nutritionist agent calls `get_nutrition`, the resulting macronutrient data is stored in the crew's context, allowing the Trainer agent to read it.

It supports SSE, Streamable HTTP, and stdio. For cloud-hosted servers on Vinkius, you will use the SSE or HTTP transport options.

Your body fat and weight metrics are transmitted directly to the API Ninjas servers via HTTPS. Vinkius acts as an ephemeral proxy, meaning no physical measurements are logged or stored in any database.

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