Cited fault codes and fluid cross-references for industrial coding and marking equipment.
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.
Diagnose a packaging/coding/marking printer fault code and return the normalised row (meaning, likely causes, checks, parts, consumables) with sources.
The fault code or message shown on the printer
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 packdesk https://packdesk.kasafox.com/mcp
Diagnose a packaging/coding/marking printer fault code and return the normalised row (meaning, likely causes, checks, parts, consumables) with sources.
| Argument | Type | Description |
|---|---|---|
| code* | string | The fault code or message shown on the printer |
| brand* | string | |
| model | string | Optional model or series |
| symptom | string | Optional free-text symptom |
{
"type": "object",
"required": [
"brand",
"code"
],
"properties": {
"code": {
"type": "string",
"description": "The fault code or message shown on the printer"
},
"brand": {
"enum": [
"Domino",
"Videojet"
],
"type": "string"
},
"model": {
"type": "string",
"description": "Optional model or series"
},
"symptom": {
"type": "string",
"description": "Optional free-text symptom"
}
}
}List the printer brands in the PackDesk dataset.
No arguments.
{
"type": "object",
"properties": {}
}Return one PackDesk fault-code row without the related-code expansion.
| Argument | Type | Description |
|---|---|---|
| code* | string | |
| brand* | string |
{
"type": "object",
"required": [
"brand",
"code"
],
"properties": {
"code": {
"type": "string"
},
"brand": {
"enum": [
"Domino",
"Videojet"
],
"type": "string"
}
}
}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.