Balena MCP. Manage IoT fleets and edge devices via natural language.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Balena MCP Server manages your entire IoT infrastructure through your AI agent. List devices, check fleet health, and manage edge deployments without leaving your chat interface.
You can dynamically create environment variables and tags, track releases, and even get download URLs for balenaOS images. It centralizes device monitoring and configuration management for large-scale edge fleets.
What your AI agents can do
Create device env var
Adds a specific environment variable to a single device's configuration.
Create device tag
Applies a custom metadata tag to a single device.
Get os download url
Retrieves the direct download URL for a specified balenaOS image version.
Use advanced OData filters to query and retrieve status information for specific devices across any defined Balena fleet.
Create specific environment variables or metadata tags on a single device to organize its hardware or apply necessary configuration flags.
List and inspect the full deployment history and available releases for an entire fleet or organization.
Query balenaOS versions for a device type and retrieve the direct download URL needed to provision a device.
Check your current user details, associated organizations, and available API keys to confirm agent permissions.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Balena MCP Server: 10 Tools for Edge Fleet Management
These tools let your AI agent query, modify, and manage every aspect of your BalenaCloud IoT infrastructure using natural language commands.
019e386acreate device env var
Adds a specific environment variable to a single device's configuration.
019e386acreate device tag
Applies a custom metadata tag to a single device.
019e386aget os download url
Retrieves the direct download URL for a specified balenaOS image version.
019e386alist api keys
Lists all API keys associated with your connected Balena account.
019e386alist devices
Queries and lists devices within specified Balena fleets using advanced filters.
019e386alist fleets
Lists all application fleets (applications) across your Balena account.
019e386alist organizations
Retrieves a list of organizations connected to your Balena account.
019e386alist os versions
Lists all available balenaOS versions for a given device type.
019e386alist releases
Lists deployment releases and their history for specific application fleets.
019e386awhoami
Gets the current user's profile details, organization list, and active API key scope.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Balena, then connect any of our 4,500+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,500+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You'll manage your whole IoT setup right through your AI agent. You don't have to jump between tabs to check on your edge devices. You can list all the fleets you've got and check what's up with 'em. You can also pull up a list of organizations connected to your Balena account.
To see which devices you're talking about, you can run list_devices, which lets you query and pull status info for specific devices across any fleet, using advanced filters. You can check what's going on with your whole setup by running list_fleets to see all your application fleets. You can check your own permissions and what your agent can do by running whoami.
For keys, you can get a list of all API keys using list_api_keys.
How Balena MCP Works
- 1 Subscribe to the Balena MCP Server and provide your API Key.
- 2 Your AI client authenticates the connection to your BalenaCloud account.
- 3 You prompt your agent with a request (e.g., 'List all devices in the Industrial-Sensor-Node fleet'). The agent runs the appropriate tool and returns the structured data.
The bottom line is, you get to manage complex IoT hardware deployments and configurations using simple conversation prompts.
Who Is Balena MCP For?
This is for the DevOps Engineer who needs to check fleet health across thousands of remote devices without opening a web dashboard. It’s for the IoT Architect who needs to programmatically verify OS versions and environment variables. It’s for the Product Owner who just needs a high-level status report on an entire organization's deployment status.
Automates environment variable updates and checks deployment release versions for large-scale device rollouts.
Uses the server to query device statuses and available balenaOS versions to plan new edge deployments.
Requests high-level overviews of fleet health and organization-wide project statuses directly through the chat.
What Changes When You Connect
- See precise device status and logs by running
list_deviceswith OData filters, eliminating the need to click through device dashboards. - Manage device metadata instantly. Use
create_device_env_varorcreate_device_tagto configure edge hardware without manual console access. - Track deployments across your entire organization. Call
list_releasesto audit which specific software version is running on which fleet. - Get OS images on demand. Use
list_os_versionsandget_os_download_urlto pull direct download links for rapid prototyping. - Audit your access rights immediately. Run
whoamito confirm your current user profile and which organizations the agent can touch. - Avoid manual dashboard navigation. By using
list_fleetsandlist_organizations, you gather high-level context before diving into device specifics.
Real-World Use Cases
Auditing a Rogue Device
An IoT engineer needs to know why a sensor node is offline. Instead of checking the dashboard, they prompt their agent: 'List devices in the Sensor-Fleet where status is down.' The agent runs list_devices and returns the exact UUID and last known status, solving the problem in one turn.
Rolling Out a New OS Version
A DevOps team needs to ensure 500 gateways are running v2.115.18. They ask the agent to list OS versions, get the URL using get_os_download_url, and then use list_releases to confirm the deployment status for the target fleet. Everything stays in the chat.
Setting up a New Hardware Batch
A Product Owner gets a new batch of edge cameras. They ask the agent to create a tag: 'Add tag location: warehouse-north to 12345.' The agent runs create_device_tag, immediately updating the device metadata without logging into the Balena console.
Checking Organization Scope
Before starting a project, an IoT Architect runs whoami to verify the agent has access to both the 'North' and 'South' organization accounts. This prevents runtime errors and confirms the necessary API scope before writing any code.
The Tradeoffs
Calling Listing Tools Separately
A developer runs list_organizations first, then copies the ID, and pastes it into a second prompt to run list_fleets with the filter. This is tedious and requires multiple back-and-forth messages.
→
Instead of sequential prompts, ask your agent to combine the steps. For example, 'List all fleets belonging to the 'Global HQ' organization.' The agent handles the filtering logic across list_organizations and list_fleets internally.
Manually Updating Metadata
The user must go to the BalenaCloud dashboard, select the device, navigate to 'Variables,' and manually input a new environment variable.
→
Just tell your agent what to do. Use the create_device_env_var tool. For example: 'Set the device variable DEBUG_LEVEL to true for device 12345.' The change happens immediately through the API call.
Ignoring Filtering Capabilities
Running list_devices with no filters, which returns a massive list of 50,000 devices, forcing the user to scroll through thousands of UUIDs to find one target device.
→
Always specify your target. Use OData filters in your prompt. Ask: 'List devices where status is down AND belongs to the 'Industrial' fleet.' This uses list_devices efficiently.
When It Fits, When It Doesn't
Use this server if your workflow involves managing physical edge hardware at scale. This is for people who need to programmatically query device status, update configuration, or track deployments across hundreds of endpoints. It's essential for CI/CD pipelines that manage IoT lifecycles.
Don't use this if you just need to view a single device's logs or perform a simple, one-time manual change that doesn't require API interaction. For those simple views, the native BalenaCloud dashboard might be faster. If you are building a generalized device inventory tool that doesn't require API calls, you don't need this. You need the ability to act on the data, not just read it.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking device status used to mean clicking through three separate dashboards.
Before, checking if your fleet was healthy meant navigating to the main dashboard, finding the application fleet, filtering by device type, and finally running a status query. This involved at least five clicks and cross-referencing three different views to confirm a single piece of data.
Now, you just tell your agent what you need. Ask: 'Show me the status of all devices in the 'Gateway' fleet.' The agent runs the `list_devices` tool and gives you a clean, filtered list of exactly what you asked for. No clicks, no confusion.
List Releases: Track Balena deployments instantly.
Manually auditing deployments meant logging into the release management section, selecting the correct organization, finding the application, and then scrolling through version logs to see if the target version was applied everywhere. It was slow and error-prone.
Now, you ask your agent to 'List the releases for the Smart-Home-Gateway fleet.' The agent executes `list_releases` and instantly provides a structured, accurate timeline of deployments across the entire organization. You know exactly what's running, period.
Common Questions About Balena MCP
How do I use the `list_devices` tool to find a specific device? +
You must use OData filters in your prompt. For example, ask: 'List devices where status is down AND belongs to the 'Industrial' fleet.' This uses list_devices efficiently and prevents you from getting a massive list.
What if I need to change a device variable after running `list_devices`? +
You don't need to run another list command. Simply tell your agent: 'Set the variable DEBUG_MODE to true for device UUID-XYZ.' The agent runs create_device_env_var directly.
Does `list_os_versions` give me a download URL? +
No, list_os_versions only lists the available versions (e.g., v2.115.18). To get the actual download link, you must run get_os_download_url and provide the specific version and device type.
How do I check if the agent can see all my API keys? +
Run the list_api_keys tool. This shows every API key linked to the account and confirms the scope of what your agent can access.
Can I list all my organizations at once? +
Yes, just run the list_organizations tool. This provides a comprehensive list of all connected organizational accounts for context.
How do I use `list_fleets` to see what applications I manage? +
The list_fleets tool shows all your active applications. You can filter the results using OData $filter, for example, to narrow down fleets by a specific slug or owner.
If I want to check a device's current environment variables, what tool should I use? +
You'll need to call list_devices and then inspect the metadata fields returned. The tool allows you to query specific devices using OData filters, which includes variable details.
What is the best way to check my user identity using `whoami`? +
whoami retrieves your current user profile, organization details, and active API keys. This confirms your credentials and shows which organizations you're connected to.
How can I find a specific device using its UUID? +
You can use the list_devices tool with an OData filter. For example, provide $filter as uuid eq '' to retrieve the exact device metadata.
Is it possible to update a device's environment variables through the AI? +
Yes! Use the create_device_env_var tool by providing the Device ID, the variable name, and the desired value. The AI will apply the change to the specific device immediately.
How do I get the download link for a specific balenaOS version? +
First, use list_os_versions to find the correct version string for your device type. Then, call get_os_download_url with the device type and version to receive the direct ZIP download URL.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Forgejo (Gitea Fork)
Manage Forgejo and Gitea instances — check version compatibility, generate API tokens, and trigger CI/CD workflows directly from your AI agent.
Vercel
Bring your Vercel deployment infrastructure into chat. Control project domains, trigger manual builds, and inspect deployment status natively.
Bunny.net
Manage Bunny.net edge infrastructure — control your CDN Pull Zones, purge caching rules, and map Storage natively from an AI agent.
You might also like
Pappers
Access French company data, financial filings, and legal documents from official business registries for due diligence research.
Mailshake
Manage cold outreach campaigns, leads, and prospects via the Mailshake REST API.
Meshy (3D AI)
Transform text and images into high-quality 3D models using Meshy's generative AI directly from your agent.