How to Use the Zeev MCP in CrewAI

Q: How does CrewAI start a workflow using Zeev?

It calls createrequest via the MCP Server. This method initializes the process, allowing the crew's specialized agents to begin working on it immediately.

Q: Can I use Zeev with CrewAI for task delegation?

Yes. The agent can use delegatetask when a specific step requires human input. It keeps the workflow moving forward while handing off work to another user.

Q: If I want to check if a process was successful using CrewAI, which tool should I use?

You can use gettask or listtasks to confirm the status. If it's done, you might need to call finishtask manually after verification.

Q: Does CrewAI require knowing the current user info when interacting with Zeev?

It helps to know who's doing what. The agent can use getme before it attempts any action, like running a process or delegating work.

Build autonomous operations and multi-agent collaboration with Zeev using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zeev MCP to CrewAI

Create your Vinkius account to connect Zeev 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 Zeev with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Multi-Step Operations

When the crew needs to start a new workflow, it uses `create_request` to kick off the process in Zeev. This means that complex operational chains—like an investigation or compliance check—run autonomously. The monitor agent tracks every step by calling tools like `get_task` and checking status updates via `list_tasks`, making sure no manual oversight is needed.

Control Workflow State

The crew needs to act decisively. If a process completes, the agent calls `finish_task`. Conversely, if something breaks mid-way, it can use `cancel_request` to shut down the flow immediately. It's crucial for autonomous operations where manual intervention isn't an option.

Discover and Inspect Processes

Before action, the crew needs intelligence. It uses `list_processes` to find all available Zeev workflows and then calls `get_process` to pull the detailed definition for analysis. This allows specialized agents to know exactly what kind of process they're supposed to interact with.

Setup guide

Set up Zeev 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 Zeev tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

It calls `create_request` via the MCP Server. This method initializes the process, allowing the crew's specialized agents to begin working on it immediately.

Yes. The agent can use `delegate_task` when a specific step requires human input. It keeps the workflow moving forward while handing off work to another user.

This MCP Server handles 'Process Definition' and 'Task'. The crew manages the full lifecycle, ensuring these definitions are accurate and current.

You can use `get_task` or `list_tasks` to confirm the status. If it's done, you might need to call `finish_task` manually after verification.

It helps to know who's doing what. The agent can use `get_me` before it attempts any action, like running a process or delegating work.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python