How to Use the Modelbit (ML Model Deployments) MCP in CrewAI

Q: How do I pass complex JSON payloads to my models?

The getinference tool on our MCP handles complex JSON payloads directly. Your agent simply formats the required feature inputs as a standard dictionary, and the tool handles the serialization to the endpoint.

Get real-time predictions directly inside your CrewAI multi-agent workflows without writing custom API integration code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modelbit (ML Model Deployments) MCP to CrewAI

Create your Vinkius account to connect Modelbit (ML Model Deployments) 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 Modelbit (ML Model Deployments) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Give CrewAI agents instant access to production ML models

Give your agents the `get_inference` tool to feed raw data directly to your deployed machine learning models. Instead of hardcoding API calls, this MCP Server lets you hand model access to any agent in your crew. The researcher agent gathers raw inputs, passes them to the model, and gets a prediction back instantly. This setup keeps your agents focused on their specific roles. You don't have to worry about managing dependencies or containerizing your models. Just define the endpoint and let your agents handle the input formatting and output parsing.

Run predictive analysis in multi-agent pipelines

Running predictive analysis in CrewAI becomes trivial when agents can call `get_inference` directly from their shared environment. One agent can clean raw user data, while a second agent uses the model to run a churn prediction. A third agent then takes that risk score and drafts a personalized retention email. Because the data flows through shared memory, the entire process happens in a single loop. You get a fully autonomous pipeline that uses your proprietary machine learning models to drive real-world actions.

Eliminate custom deployment glue code

Stop wasting hours writing custom Flask wrappers when the `get_inference` tool handles the connection details under the hood. This MCP Server gives you a clean interface that works out of the box. You supply the model endpoint, and the tool handles the serialization and network requests. It keeps your codebase clean, readable, and incredibly easy to maintain as your model portfolio grows.

Setup guide

Set up Modelbit (ML Model Deployments) 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 Modelbit (ML Model Deployments) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Modelbit (ML Model Deployments) 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="Modelbit (ML Model Deployments) Analyst",
        goal="Access and analyze Modelbit (ML Model Deployments) data via MCP.",
        backstory="Expert analyst with direct Modelbit (ML Model Deployments) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Modelbit (ML Model Deployments) 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 Modelbit. 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 Modelbit (ML Model Deployments) 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 Modelbit (ML Model Deployments) MCP in CrewAI

You pass the server URL directly into the agent's tools list during initialization. Use the mcps parameter in your agent configuration, and the framework automatically exposes the tool to that specific agent.

Yes, agents share access to the tool through their collaborative environment. One agent can fetch inputs while another concurrent agent executes the inference tool to process predictions.

Latency depends on your model's complexity and cold-start times. The wrapper adds virtually zero overhead, meaning you get the raw execution speed of your deployed endpoint.

The `get_inference` tool on our MCP handles complex JSON payloads directly. Your agent simply formats the required feature inputs as a standard dictionary, and the tool handles the serialization to the endpoint.

Yes, your feature vectors and raw inference input payloads are processed within an isolated V8 sandbox. We handle the endpoint token securely, ensuring your proprietary data never leaks to external logs or third-party training sets.

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