Compatible with every major AI agent and IDE
What is the Balena MCP Server?
Connect your BalenaCloud account to any AI agent to orchestrate your IoT infrastructure through natural language. Monitor device health, manage fleet configurations, and handle deployments without leaving your chat interface.
What you can do
- Fleet & Device Monitoring — List all fleets (applications) and query specific devices using OData filters for precise status updates.
- Configuration Management — Dynamically create device-specific environment variables and metadata tags to organize your edge hardware.
- Release Tracking — Inspect deployment history and releases across your organizations to ensure your fleet is running the correct software.
- OS Provisioning — Query available balenaOS versions for specific device types and retrieve direct download URLs for rapid prototyping.
- Identity Management — Verify your current user profile, organizations, and active API keys associated with your account.
How it works
- Subscribe to this server
- Enter your Balena API Key
- Start managing your edge infrastructure from Claude, Cursor, or any MCP-compatible client
Who is this for?
- IoT Engineers — quickly check device statuses or logs without navigating the BalenaCloud dashboard.
- DevOps Teams — automate environment variable updates and release inspections during deployment cycles.
- Product Owners — get high-level overviews of fleet health and organization-wide project statuses.
Built-in capabilities (10)
Create a device environment variable
Create a device tag
Get the download URL for a balenaOS image
List Balena API keys
Use OData $filter, $select, and $expand for advanced querying (e.g., $filter=uuid eq '<UUID>'). List devices in Balena fleets
Use OData $filter, $select, and $expand for advanced querying (e.g., $filter=slug eq '<SLUG>'). List Balena fleets (applications)
List Balena organizations
g., raspberrypi3). List available balenaOS versions for a device type
Use OData $filter to filter by fleet (e.g., $filter=belongs_to__application eq <FLEET_ID>). List Balena releases
Get current Balena user details
Why Mastra AI?
Mastra's agent abstraction provides a clean separation between LLM logic and Balena tool infrastructure. Connect 10 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.
- —
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Balena without touching business code
- —
Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation
- —
TypeScript-native: full type inference for every Balena tool response with IDE autocomplete and compile-time checks
- —
One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure
Balena in Mastra AI
Balena and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Balena to Mastra AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Balena in Mastra AI
The Balena MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Mastra AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Balena for Mastra AI
Every tool call from Mastra AI to the Balena MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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 '<YOUR_UUID>' 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.
How does Mastra AI connect to MCP servers?
Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
Can Mastra agents use tools from multiple servers?
Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
Does Mastra support workflow orchestration?
Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.
createMCPClient not exported
Install: npm install @mastra/mcp
Explore More MCP Servers
View all →
Zenkit
8 toolsManage workspaces, lists, and entries via the Zenkit API.

AdButler
5 toolsAd serving and reporting — manage publishers, zones, campaigns, and ad performance via AI.

Goaffpro
12 toolsManage affiliates, track referral orders, and oversee commissions via AI agents with Goaffpro.

USCIS Case Status (Immigration)
1 toolsTrack USCIS immigration case statuses and processing history directly from your AI agent using receipt numbers.
