labelixa-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LABELIXA_API_KEY | No | Optional `lbx_` API key. Without it the anonymous quota applies. Get a key at https://labelixa.com. | |
| LABELIXA_BASE_URL | No | Optional base URL for the Labelixa API. Defaults to https://api.labelixa.com. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| zpl_previewA | Render ZPL label code to a PNG image via the Labelixa API. This is a SERVER-SIDE render for inspection — it is not a guarantee of how a specific physical printer will output the label. |
| zpl_validateA | Pass/fail lint for ZPL: machine-readable diagnostics with line/column, code and severity (unknown commands, parameter range errors, layout overflow). Fast; run it before zpl_preview whenever you generate or edit ZPL. For a human-readable report with a score use explain_zpl instead. Pass the real label size — checks depend on it. |
| barcode_generateA | Generate a standalone barcode (SVG text or PNG image). Supported types include code128, code39, ean13, upca, upce, itf14, msi, qrcode, datamatrix, pdf417. |
| language_detectA | Detect which printer language raw label code is written in (ZPL, EPL, TSPL or CPCL). Heuristic: returns the language plus a confidence TIER (high/medium/low) and signal codes — not a probability. |
| epl_validateA | Lint/validate EPL/EPL2 label code and return the structured diagnostics report (findings with positions and severity) as JSON. |
| tspl_validateA | Lint/validate TSPL/TSPL2 label code and return the structured diagnostics report (findings with positions and severity) as JSON. |
| cpcl_validateB | Lint/validate CPCL label code and return the structured diagnostics report (findings with positions and severity) as JSON. |
| zpl_compatibilityA | Compatibility RISK analysis of ZPL code against a specific printer model, given as manufacturer/model (e.g. 'zebra/zd421'). NOT an emulator and never says 'it works': reports the model's language posture with evidence level, size-rule findings and the scope of our preview. |
| zpl_command_helpA | Look up one ZPL command in the maintained catalog: name, syntax, parameters (types, ranges, defaults) and whether the preview engine actually renders it — printer-side commands are honestly marked as not rendered. |
| convert_zpl_dpiA | Rescale ZPL coordinates between printer resolutions (203/300/600 dpi). Embedded ^GF/~DG bitmap data is NOT rescaled — when present, a Warnings block precedes the output instead of silently passing. |
| explain_zplA | Human-readable health REPORT for a finished ZPL label with a 0-100 score, sectioned (syntax, size/DPI, orientation, barcodes, fonts, memory): only assessable sections count, the rest say 'not assessed'. Use it to review or explain a label to a person; for a quick pass/fail check while editing use zpl_validate. Pass the real label size — findings depend on it. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Tools mostly target clearly distinct operations: per-language validators (zpl/epl/tspl/cpcl_validate) are unambiguous, and the descriptions explicitly contrast explain_zpl vs zpl_validate and zpl_preview vs zpl_compatibility. The only mild overlap is the human-report vs pass/fail pair, which the descriptions do resolve, so nothing causes real misselection.
All names are snake_case and mostly follow a language_verb or verb_language pattern, but verb placement is inconsistent (zpl_validate vs explain_zpl, convert_zpl_dpi) and some use extra nouns (zpl_command_help) while others are generic (barcode_generate, language_detect). Readable but not a single predictable convention.
With 11 tools the set sits comfortably in the well-scoped 3-15 range, and each tool covers a distinct capability (validate, explain, preview, convert, lookup, detect, barcode, compatibility) rather than redundant variants.
ZPL has full lifecycle coverage (validate, explain, preview, dpi conversion, command help, compatibility), but EPL, TSPL and CPCL only get a validate tool—no preview, explain, conversion or command lookup for those languages. This asymmetry is a notable gap for a multi-language label server, though agents can still work around it via ZPL-first workflows.