How to Use the Nyckel ML MCP in CrewAI

Q: How do I add semantic search to my CrewAI agents?

Pass the semanticsearch tool into the agent's MCP list. Each agent gains the ability to find relevant data points across your indices.

Q: Can I filter which tools my CrewAI agents can access?

You use the toolfilter option to restrict an agent to specific tools like invokemlfunction. This keeps your specialized agents focused.

Deploy specialized agent crews in CrewAI that classify data and manage training samples autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nyckel ML MCP to CrewAI

Create your Vinkius account to connect Nyckel ML 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 Nyckel ML with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous classification crews in CrewAI

Assign `invoke_ml_function` to a research agent to classify incoming data streams. Other agents in your crew then consume these results to perform deeper analysis. This role-based setup lets you separate the classification task from the decision-making logic. Your crew operates as a cohesive unit to process data at scale.

Shared memory for ML tasks in CrewAI

Use `list_ml_labels` and `list_ml_samples` so your crew maintains a shared understanding of your current dataset. Agents can cross-reference existing samples before adding new ones. This prevents redundant work across your agents. They coordinate their actions based on the current state of your ML models.

Self-maintaining ML models in CrewAI

Configure your crew to use `annotate_ml_sample` for active learning loops. As agents find new information, they update your model labels without human intervention. Your agents watch the model output and refine it as they work. It creates a system that improves itself as it processes more data.

Setup guide

Set up Nyckel ML 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 Nyckel ML tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Nyckel ML 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 Nyckel. 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 Nyckel ML 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 Nyckel ML MCP in CrewAI

Pass the `semantic_search` tool into the agent's MCP list. Each agent gains the ability to find relevant data points across your indices.

You use the tool_filter option to restrict an agent to specific tools like `invoke_ml_function`. This keeps your specialized agents focused.

You pass the server URL directly into the agent definition. CrewAI handles the transport and tool registration automatically.

The agent reports the failure back to the crew manager. You can configure your crew to retry or escalate the task to a human moderator.

Yes, every sample is stored in a private container accessible only via your unique endpoint token. No other users or agents can access your dataset.

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

Mastra AI sdk-typescript

Start using the Nyckel ML MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started