shelly-mcp
Related Servers
Alternatives to shelly-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityCmaintenanceMCP server for controlling Somfy TaHoma devices locally via the box's API, without cloud dependency.-
- AlicenseBqualityCmaintenanceMCP server for full Home Assistant control, enabling AI agents to manage dashboards, automations, files, apps, entities, and more via REST API, WebSocket, and SSH.66170 npmMIT
- AlicenseAqualityDmaintenanceMCP server for Hubitat Elevation hubs that controls devices via the Maker API, with optional gated access to undocumented admin routes, supporting device listing, command sending, virtual device and hub variable automation for Rule Machine, and hub management features.8MIT
- AlicenseNot gradedqualityDmaintenanceA LAN-first, cloud-fallback MCP server for controlling Govee smart devices by name. It enables AI agents or MCP clients to manage lights, plugs, and appliances with commands like power, brightness, color, and scenes.44 PyPIMIT
- AlicenseAqualityAmaintenanceMCP server for administering a Zigbee2MQTT estate, enabling mesh health monitoring, device management, firmware updates, pairing, binding, and reporting via natural language.17133 npm36MIT
- AlicenseAqualityDmaintenanceMCP server for controlling Homey Pro smart home systems, offering 60+ tools for device control, flow authoring, automation, monitoring, and network diagnostics.601MIT
TDQS
Scored across 47 tools
Almost every tool has a distinct resource+action target, and descriptions sharply differentiate read vs. write (shelly_rpc vs shelly_rpc_write) and info vs. status vs. config. The only real overlap is shelly_list_devices vs shelly_discover (both enumerate devices), though the LAN-mDNS vs. known/cloud distinction is spelled out. Minor boundary blurring keeps it just under perfect.
Uniform shelly_ prefix and snake_case throughout, with domain-grouped names (scene_, schedule_, script_, kvs_, webhook_, virtual_) that are highly predictable. The one deviation is the control group using noun_verb (switch_set, light_set, cover_move) vs. verb_noun elsewhere (list_components, get_status), which is consistent within its group but not across the whole set.
47 tools is heavy (well above the ~15 ideal) and will burden selection, but the surface genuinely spans many independent subsystems — devices, KVS, scenes, schedules, scripts, webhooks, virtual components, energy, and system ops — each legitimately needing CRUD. It is large but not a mismatch the way a 50+ grab-bag would be.
Near-complete lifecycle coverage: CRUD for KVS, schedules, webhooks, scripts, and virtual components; create/run/delete for scenes (with overwrite covering update); device discovery, info, status, config, energy live+history, and system reboot/update/auth. The read/write RPC escape hatches (shelly_rpc, shelly_rpc_write) close any residual gaps, leaving no obvious dead ends.