Cited fault codes for solar, ESS and EV inverters: causes, checks, parts and safety flags.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Look up a solar / ESS / EV inverter or charge-controller fault code and return the normalised meaning, likely causes, checks, parts, safety notes, and source. Cite the source and hard-stop (requires_qualified_installer) on safety-critical faults.
The code shown on the display or app, e.g. 'Err 17', 'VE.Bus Error 8'
Inverter/charger brand
Optional model or series
Optional free-text symptom
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http solardesk https://solardesk.kasafox.com/mcp
Look up a solar / ESS / EV inverter or charge-controller fault code and return the normalised meaning, likely causes, checks, parts, safety notes, and source. Cite the source and hard-stop (requires_qualified_installer) on safety-critical faults.
| Argument | Type | Description |
|---|---|---|
| code* |
| string |
| The code shown on the display or app, e.g. 'Err 17', 'VE.Bus Error 8' |
| brand* | string | Inverter/charger brand |
| model | string | Optional model or series |
| symptom | string | Optional free-text symptom |
{
"type": "object",
"required": [
"brand",
"code"
],
"properties": {
"code": {
"type": "string",
"description": "The code shown on the display or app, e.g. 'Err 17', 'VE.Bus Error 8'"
},
"brand": {
"enum": [
"Fronius",
"Growatt",
"SMA",
"SolarEdge",
"Victron"
],
"type": "string",
"description": "Inverter/charger brand"
},
"model": {
"type": "string",
"description": "Optional model or series"
},
"symptom": {
"type": "string",
"description": "Optional free-text symptom"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.