How to Use the Balena MCP in CrewAI

Q: How do I connect my CrewAI agents to the Balena MCP Server?

Install crewaitools via pip. Add your Vinkius endpoint directly to the mcps array in your Agent definition. The framework handles the HTTP transport automatically.

Q: How do I limit which tools an agent can use?

Import MCPServerHTTP from crewai.mcp instead of using the simple URL string. Pass a toolfilter list containing only the specific operations that agent needs.

Deploy autonomous multi-agent teams to monitor, diagnose, and update your Balena edge devices with CrewAI and this 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 Balena MCP to CrewAI

Create your Vinkius account to connect Balena 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 Balena with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign specialized IoT management roles

A diagnostic agent uses the `list_devices` tool to sweep your fleet for offline units. It filters the OData response for specific error states and passes the UUIDs into shared memory. The system runs autonomously without a human sitting at a dashboard. Next, a remediation agent picks up those failed UUIDs. It runs `list_releases` to check the current firmware baseline against the expected application state, deciding if a rollback is necessary.

Chain Balena MCP Server operations

CrewAI executes tasks in strict order when running the `list_organizations` tool to map tenant boundaries. The process starts by verifying access controls before touching any hardware. Then it calls `list_fleets` to isolate the target application group. Finally, the execution agent applies the fix using `create_device_env_var`. It injects the new configuration payload into the exact devices identified in the previous steps.

Restrict agent access to specific tools

Restricting an agent from using the `list_api_keys` tool prevents autonomous security breaches. By using `MCPServerHTTP` and `tool_filter`, you restrict the monitoring agent to read-only operations like `whoami` and `list_os_versions`. Meanwhile, only the senior moderation agent gets access to `create_device_tag` and variable creation. This strict separation of concerns prevents a hallucinating research agent from accidentally modifying production hardware.

Setup guide

Set up Balena 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 Balena tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai[tools]` via pip. Add your Vinkius endpoint directly to the `mcps` array in your Agent definition. The framework handles the HTTP transport automatically.

Yes. The agent constructs OData queries for the tools. It sends `$filter=uuid eq ''` to pull isolated telemetry instead of downloading the entire global device registry.

Agents pass tool outputs to each other during execution. If Agent A fetches firmware versions, Agent B can read that context to decide which devices need patching.

Import `MCPServerHTTP` from `crewai.mcp` instead of using the simple URL string. Pass a `tool_filter` list containing only the specific operations that agent needs.

The connection reads fleet IDs, device tags, OS versions, and environment variables. Vinkius processes these operations inside an ephemeral sandbox. The connection closes immediately after the agent finishes its task, leaving no trace.

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