coolercontrol-mcp
Related Servers
Alternatives to coolercontrol-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceUnofficial MCP server for Hive (British Gas) smart heating. Lets Claude and other AI assistants check your thermostats, radiator valves, hot water, plugs and lights and, if you allow it, boost the heating, set temperatures, switch on the hot water and set holiday mode. Read-only by default, with an optional audit log of every change. Runs in Docker or as a one-click Claude Desktop bundle.MIT
- AlicenseNot gradedqualityCmaintenanceConnects MCP clients such as Claude to a NIBE myUplink heat-pump account, letting users list systems and devices, read sensor values and common parameters, check alarms, view smart-home zones, and write settings where scopes allow. Handles the OAuth2 authorization-code and client-credentials flows, refreshing tokens automatically while keeping credentials in a local .env file.MIT
- AlicenseAqualityBmaintenanceEnables MCP-compatible clients like Claude Desktop, Claude Code, Codex, and local-model hosts to inspect Proxmox VE clusters, nodes, VMs, containers, storage, snapshots, and tasks, with opt-in write operations for starting, stopping, cloning, backing up, and migrating guests. Read-only by default, it supports both stdio and Streamable HTTP transports.14MIT
- AlicenseNot gradedqualityCmaintenanceEnables local, cloud-free control of Daikin air conditioners from MCP clients, letting assistants read unit state and adjust power, mode, temperature, fan, louvres, and special modes over the unit's local HTTP API.MIT
- 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 gradedqualityCmaintenanceEnables MCP clients to discover NVIDIA, AMD, and Intel GPUs, monitor utilization, memory, temperature, power, clocks, and processes, retain bounded local history, and estimate whether AI models fit available VRAM before loading them.MIT
TDQS
Scored across 32 tools
Tools are grouped by distinct resources and actions (profiles, modes, functions, alerts, custom sensors, channel operations), and most boundaries are clear. The main ambiguity is the generic call_api/list_api_endpoints pair, which overlaps every dedicated tool, but the description explicitly steers agents toward dedicated tools when available.
All tool names use consistent snake_case with predictable verb_noun or action_resource structure. Variations like activate_mode, apply_profile, reset_channel, and set_fixed_speed are specific but still follow the same convention.
32 tools is heavy for a fan-control server, even though the domain has many subresources with full CRUD families. Several conveniences (duplicate_mode) and meta-REST tools push the set beyond a tightly scoped surface, making it borderline over-scoped.
The set covers CRUD for modes, profiles, functions, alerts, and custom sensors, plus device/status reads and channel assignment/reset operations. The list_api_endpoints/call_api escape hatch also fills gaps for lighting, LCD, calibration, and other daemon endpoints.