"PocketBase-Cursor-MCP server by Minhdtb" matching MCP servers:

Enables Cursor and other MCP-compatible agents to control a Stack-chan robot companion, giving the AI vision, hearing, speech, movement, facial expressions, and environmental sensing.

Enables agents to drive a Coreflux broker end to end over MQTT: running broker commands, publishing and subscribing to live topics, linting and deploying LoT/.lotnb files in order, uploading and exporting projects, tracing actions, and searching docs. Destructive operations are gated behind safety hooks, and no npm dependencies are required beyond Node.js 20+.

Connect AI assistants to industrial OPC UA systems. Browse nodes, read live data and history, and monitor subscriptions, events and alarms. Runs locally over stdio in read-only mode by default.

Gives PC AI agents real-world senses by connecting to an Android phone's camera, sensors, and files over local Wi-Fi without cloud relay or ADB.

Lets an MCP client control an NVIDIA Shield TV over the Android TV Remote protocol v2 by pressing remote keys, launching allow-listed apps, waking or sleeping the device, and reading its power state and foreground app.

Enables AI agents to build freeform dashboards for e-ink panels by listing widgets and devices, laying out a canvas, rendering a preview, and pushing to the panel.

Enables AI clients to discover, occupy, and operate LAN hardware devices that speak the BMAHS protocol by mapping their actions to MCP tools.

Control your DCC model railroad by voice or chat through any MCP client, with dynamic discovery of layout elements from JMRI.

Enables control of SwitchBot devices by name, reducing the risk of AI misidentifying device IDs.

Enables Claude to analyze STL/3MF models, slice them with the real Bambu Studio engine, compare print recipes by time and weight, and manage presets for Bambu Lab printers. It produces ready-to-print .3mf project files with material and build-plate settings applied, all locally on the user's PC.

Enables Claude Desktop to control serial-port devices like network craft ports, radios, rotators, and microcontrollers by sending commands and reading responses until a prompt or available output.

Enables LLM clients to discover, occupy, and control BMAHS protocol hardware devices on the local network by dynamically exposing device operations as MCP tools.

Central user-state database MCP server with durable profile facts and live virtual sensors (stress, room intensity) with configurable smoothing, readable by any agent or smart-home service.

Connects Home Assistant media players to Cursor, allowing automated control of playback (play/pause) based on agent activity for dopamine-driven development breaks.

Gives AI assistants structured, read-only-by-default access to Hobart commercial dishwashers through the SmartConnect Cloud-to-Cloud API, covering machine lists, active errors, wash and rinse temperatures, daily water/energy/detergent consumption, and per-cycle hygiene records. Optional write tools, off unless explicitly enabled and confirmed, allow registering machines and adjusting dosage, density, and autostart settings.

Exposes Justworx devices to AI agents as MCP tools and resources, backed by the public Developer API. Supports local stdio and hosted remote OAuth operation for controlling device IO, rules, and viewing live state.

Connects Claude and other MCP clients to myGEKKO building controllers via the official Query API, enabling natural-language queries and control of smart-home devices. It is read-only by default, with write actions available only through explicit opt-in and safety policies.

Enables controlling ecobee thermostats from ChatGPT by connecting a user's ecobee account through normal browser sign-in, without an ecobee developer API key. Supports listing thermostats, reading status, setting temperature or HVAC mode, and resuming schedules.

Enables AI clients to read and control local ecobee thermostats over HomeKit, listing thermostats, getting status, setting or adjusting temperatures, changing HVAC modes, and holding or resuming comfort settings per thermostat or house-wide. Changes are constrained by guardrails such as setpoint limits, an optional read-only mode, and a per-thermostat hourly change cap, with every attempt logged.

Enables AI assistants to monitor a Hyundai, Kia, or Genesis vehicle's charge, fuel, range, locks, and location, and optionally pre-heat the cabin, lock or unlock doors, and start or stop charging. Reads come from cached Bluelink data with rate-limited refreshes, and all write commands are disabled by default.

Enables MCP clients to manage a self-hosted RPort fleet by listing and inspecting connected devices, opening and closing SSH tunnels, and executing commands through RPort agents.

Query and control Orbit B-Hyve irrigation systems from MCP-compatible clients like Claude Code and Cursor.

MCP server for Home Assistant — 202 tools across 21 domains; full control of your smart home from Claude / Cursor / VS Code / any MCP client

Enables Cursor to subscribe to MQTT topics and read buffered messages from an MQTT broker.

Enables an AI agent to control one or more remote GPIO agents through a conversation by proxying tool calls to their REST APIs. It supports API-key authentication, LAN discovery, and both stdio and Streamable HTTP transports.

Lets an AI assistant inspect and adjust TP-Link Omada WiFi networks by searching, describing, and calling any of roughly 1,650 Omada Open API operations through nine tools. It is read-only by default, refusing every non-GET request unless writes are explicitly unlocked, and even then returning a dry-run preview until a change is confirmed.

Enables MCP clients to query robot lawn mower specs, prices, 0-5 scores, comparisons, and buying recommendations from a curated CC BY 4.0 dataset.

Enables an AI assistant such as Claude to operate a Duet machine (RepRapFirmware) over LAN/WLAN by reading status, managing files, viewing camera snapshots, homing axes, and starting or supervising prints while enforcing safety approvals and guards.

Enables MCP-speaking coding agents to talk directly to Home Assistant and the ESPHome dashboard: discovering entities and areas, reading live states, history and logs, rendering Jinja templates, calling services, and creating, editing or triggering automations and dashboards. Also allows ESPHome device configs to be read, validated, compiled and flashed, with all write operations off by default behind an explicit safety policy.

A Model Context Protocol (MCP) integration that allows AI assistants to control Home Assistant devices by searching for entities and controlling devices through natural language commands.