Compatible with every major AI agent and IDE
What is the ESPHome MCP Server?
Connect your ESPHome microcontrollers to any AI agent and take full control of your smart home or industrial IoT setup through natural conversation.
What you can do
- Real-time Monitoring — Fetch the current state and values of any sensor, switch, or binary sensor using the
get_entity_statetool. - Lighting Control — Manage lights with precision using
light_action, including brightness and RGB color adjustments. - Appliance Management — Toggle switches, control fans with
fan_action, and adjust covers (blinds/garage doors) withcover_action. - Interactive Components — Press buttons via
button_press, set numeric values withnumber_set, and choose options from dropdowns withselect_option. - Security & Safety — Arm or disarm alarm panels using
alarm_actiondirectly from your chat interface.
How it works
- Enable the
web_servercomponent in your ESPHome YAML configuration. - Subscribe to this server.
- Enter your device's local URL and optional password.
- Start interacting with your hardware from Claude, Cursor, or any MCP client.
Who is this for?
- Home Automation Enthusiasts — control your local environment without complex dashboards.
- IoT Developers — test and debug ESP32/ESP8266 entity behaviors using natural language.
- Hardware Engineers — monitor sensor metrics and trigger actions during prototyping phases.
Built-in capabilities (10)
Perform an action on an alarm control panel
Press a button entity
g., blinds, garage door), optionally setting position and tilt. Perform an action on a cover entity
Perform an action on a fan entity
g., sensor, switch) using the Web Server REST API. Get the state of an ESPHome entity
Get Prometheus metrics from the ESPHome device
Perform an action on a light entity
Set a value for a number entity
Set an option for a select entity
Perform an action on a switch entity
Why Cursor?
Cursor's Agent mode turns ESPHome into an in-editor superpower. Ask Cursor to generate code using live data from ESPHome and it fetches, processes, and writes. all in a single agentic loop. 10 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
ESPHome in Cursor
ESPHome and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect ESPHome to Cursor 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 ESPHome in Cursor
The ESPHome 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 Cursor 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
ESPHome for Cursor
Every tool call from Cursor to the ESPHome MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I control my lights and set specific colors using this server?
Yes! Use the light_action tool. You can specify the entity name, the action (turn_on), and optional parameters like brightness (0-255) and RGB values (r, g, b) to get the perfect ambiance.
How do I check the current temperature or humidity from my sensors?
Simply use the get_entity_state tool. Provide the domain (e.g., 'sensor') and the entity ID. The agent will return the current value and state of that specific hardware component.
Is it possible to trigger a physical button or restart a device?
Yes. If you have a button entity configured in ESPHome (like a restart button), you can use the button_press tool with the entity name to trigger that action remotely.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Chili Piper
8 toolsManage scheduling and lead routing via Chili Piper — track meetings, monitor queues, and manage teams directly from any AI agent.

SemVer Version Manager
2 toolsStop LLMs from guessing software versions. Deterministically evaluate semantic version bounds, compatibilities, and sort releases perfectly.

Product Hunt Alternative
4 toolsAccess Product Hunt data directly — browse daily posts, execute custom GraphQL queries, and manage your viewer profile via AI.

Chuanyun
10 toolsEnterprise workflow automation and digital engine — manage business objects, forms, and approval history via AI.
