How to Use the zrok (Open-Source Tunnel) MCP in CrewAI

Q: How does zrok (Open-Source Tunnel) help autonomous operations with CrewAI?

The MCP Server provides the tools. An agent can call listshares to check tunnel availability, and another agent handles the subsequent action, like calling createshare if a new tunnel is needed.

Q: If I need to monitor environmental changes with zrok (Open-Source Tunnel) in CrewAI, what should I use?

You'll use the combination of listenvironments and getaccount. The monitoring agent first checks the available environments, then verifies if account limits are being hit.

Q: Can I manage zrok (Open-Source Tunnel) credentials for agents using CrewAI?

Yes. Agents collaborate by having one call loginaccount to get a valid token. This token is then passed as context or input to subsequent tools used by other specialized agents.

Q: What happens if an agent needs to clean up resources using zrok (Open-Source Tunnel) with CrewAI?

The final action in the crew's workflow is calling deleteshare. This ensures that every temporary tunnel created during the operation gets cleaned up automatically.

Build autonomous operations using zrok (Open-Source Tunnel) with CrewAI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect zrok (Open-Source Tunnel) MCP to CrewAI

Create your Vinkius account to connect zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Tunnel Setup and Teardown

A specialized agent can use `zrok (Open-Source Tunnel)`'s tools to manage resources autonomously. For example, one agent calls `create_share` when the task starts. A different monitor agent watches this process and is programmed to call `delete_share` once the required research or analysis is complete.

Contextual Environment Awareness

When setting up a complex operation, one agent needs to know which networks are active. It uses `list_environments`, and another agent can then call `enable_environment` if the necessary resources aren't available. This ensures that autonomous operations always run within the correct, pre-approved network context.

Secure Credential Management for Agents

Agents need credentials to operate. One agent can call `login_account` and pass the received token result to another agent's tool definition. This structure allows multiple specialized agents to share a single, valid access context without any human intervention.

Setup guide

Set up zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent zrok (Open-Source Tunnel) 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 zrok. 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 zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) MCP in CrewAI

The MCP Server provides the tools. An agent can call `list_shares` to check tunnel availability, and another agent handles the subsequent action, like calling `create_share` if a new tunnel is needed.

You'll use the combination of `list_environments` and `get_account`. The monitoring agent first checks the available environments, then verifies if account limits are being hit.

Yes. Agents collaborate by having one call `login_account` to get a valid token. This token is then passed as context or input to subsequent tools used by other specialized agents.

The final action in the crew's workflow is calling `delete_share`. This ensures that every temporary tunnel created during the operation gets cleaned up automatically.

The tool returns details about active tunnels, including their status and visibility (public or private). This information is key for the agents to determine if a resource already exists.

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