Labelixa
Thermal label MCP server: render, validate, debug and convert ZPL, EPL, TSPL and CPCL labels.
我该使用它吗
质量与安全性
发现（5）
- HIGHTool poisoning patterns detected
- MEDIUMTool 'bulk_submit' description contains placeholder text在 bulk_submit 中
- LOWTool 'language_detect' description lacks action verb在 language_detect 中
- LOWTool 'convert_zpl_dpi' description lacks action verb在 convert_zpl_dpi 中
- INFOTool description contains placeholder or incomplete text在 bulk_submit 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"zpl": {
"command": "npx",
"args": [
"labelixa-mcp"
]
}
}
}可运行的软件包
0.4.1stdio远程端点
https://api.labelixa.com/mcpstreamable-http它能做什么
工具清单
工具（21）
🟢zpl_preview(zpl, dpmm, width_in, height_in, index)
Render ZPL label code and return the label as a PNG image. Use this to SEE what ZPL output looks like — LLMs can write ZPL but cannot otherwise verify the visual result. One call renders one label (use `index` to pick a label from a multi-label stream). The result also carries an 'Open this label in the Labelixa editor' link the user can click to edit, save or share the label.
输入模式
{
"type": "object",
"properties": {
"zpl": {
"type": "string",
"description": "ZPL source (^XA...^XZ)"
},
"dpmm": {
"type": "integer",
"enum": [
6,
8,
12,
24
],
"default": 8,
"description": "Printer density (8 = 203 dpi)"
},
"width_in": {
"type": "number",
"default": 4,
"description": "Label width, inches"
},
"height_in": {
"type": "number",
"default": 6,
"description": "Label height, inches"
},
"index": {
"type": "integer",
"default": 0,
"description": "Label index in the stream"
}
},
"required": [
"zpl"
]
}🟢zpl_validate(zpl, dpmm, width_in, height_in)
Lint ZPL code and return structured diagnostics: unknown commands, missing ^FS, out-of-range parameters, fields outside the label boundary. Run this before zpl_preview when generating ZPL.
输入模式
{
"type": "object",
"properties": {
"zpl": {
"type": "string",
"description": "ZPL source"
},
"dpmm": {
"type": "integer",
"default": 8,
"description": "Printer density (8 = 203 dpi). The boundary check measures against it — pass the real value."
},
"width_in": {
"type": "number",
"default": 4,
"description": "Label width in inches. Fields outside it are reported, so a wrong size makes that finding wrong."
},
"height_in": {
"type": "number",
"default": 6,
"description": "Label height in inches. Same as width_in: the boundary check depends on it."
}
},
"required": [
"zpl"
]
}输出模式
{
"type": "object",
"properties": {
"diagnostics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Stable diagnostic code, e.g. ZPL0002"
},
"severity": {
"type": "string",
"enum": [
"error",
"warning",
"info"
]
},
"message_key": {
"type": "string",
"description": "i18n key for the message"
},
"mesaj": {
"type": "string",
"description": "Human-readable message in the requested language"
},
"line": {
"type": "integer"
},
"col": {
"type": "integer"
},
"end_line": {
"type": "integer"
},
"end_col": {
"type": "integer"
}
},
"required": [
"code",
"severity",
"line",
"col"
]
}
},
"ozet": {
"type": "object",
"properties": {
"toplam": {
"type": "integer"
},
"error": {
"type": "integer"
},
"warning": {
"type": "integer"
},
"info": {
"type": "integer"
}
},
"required": [
"toplam",
"error",
"warning",
"info"
]
},
"alanlar": {
"type": "array",
"items": {
"type": "object",
"properties": {
"line": {
"type": "integer"
},
"x": {
"type": "integer"
},
"y": {
"type": "integer"
}
}
}
},
"rfid": {
"type": "array",
"items": {
"type": "object"
}
}
},
"required": [
"diagnostics",
"ozet"
]
}🟢zpl_command_help(command, locale)
Explain a single ZPL command: syntax, parameters with types/ranges/options, a fragment example and whether the Labelixa renderer draws it. Data comes from the same catalog that powers the public command reference pages.
输入模式
{
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "ZPL command code, e.g. FO, ^BC, ~DG"
},
"locale": {
"type": "string",
"enum": [
"en",
"tr",
"de"
],
"default": "en",
"description": "Language for the human-readable fields (name and descriptions). Command codes, syntax strings, examples and parameter names never change."
}
},
"required": [
"command"
]
}🟢barcode_png(type, data)
Generate a single barcode as a PNG image (Code 128, QR, DataMatrix, EAN-13, UPC-A, PDF417 and more). For a full label with text and layout, write ZPL and use zpl_preview instead.
输入模式
{
"type": "object",
"properties": {
"type": {
"type": "string",
"default": "code128",
"description": "Symbology (code128, qr, datamatrix, ean13, upca, pdf417...)"
},
"data": {
"type": "string",
"description": "Data to encode"
}
},
"required": [
"data"
]
}🟢language_detect(code)
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.
输入模式
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Raw label code to classify"
}
},
"required": [
"code"
]
}输出模式
{
"type": "object",
"properties": {
"dil": {
"type": "string",
"description": "Detected printer language"
},
"guven": {
"type": "string",
"description": "Confidence level"
},
"karma": {
"type": "boolean",
"description": "True when the input mixes languages"
},
"puanlar": {
"type": "object",
"description": "Per-language score",
"additionalProperties": {
"type": "integer"
}
},
"kanitlar": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kod": {
"type": "string"
},
"satir": {
"type": "integer"
}
}
}
}
},
"required": [
"dil",
"guven",
"puanlar"
]
}🟢epl_validate(epl)
Lint EPL/EPL2 label code and return positioned findings with severity as JSON. Checks the command set Labelixa implements from the EPL2 manual — a clean result is not a guarantee that a specific printer accepts the job. Run this before epl_preview; if you are not sure which language the code is, call language_detect first.
输入模式
{
"type": "object",
"properties": {
"epl": {
"type": "string",
"description": "Raw EPL/EPL2 code"
}
},
"required": [
"epl"
]
}输出模式
{
"type": "object",
"properties": {
"diagnostics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Stable diagnostic code, e.g. ZPL0002"
},
"severity": {
"type": "string",
"enum": [
"error",
"warning",
"info"
]
},
"message_key": {
"type": "string",
"description": "i18n key for the message"
},
"mesaj": {
"type": "string",
"description": "Human-readable message in the requested language"
},
"line": {
"type": "integer"
},
"col": {
"type": "integer"
},
"end_line": {
"type": "integer"
},
"end_col": {
"type": "integer"
}
},
"required": [
"code",
"severity",
"line",
"col"
]
}
},
"ozet": {
"type": "object",
"properties": {
"toplam": {
"type": "integer"
},
"error": {
"type": "integer"
},
"warning": {
"type": "integer"
},
"info": {
"type": "integer"
}
},
"required": [
"toplam",
"error",
"warning",
"info"
]
}
},
"required": [
"diagnostics",
"ozet"
]
}🟢tspl_validate(tspl)
Lint TSPL/TSPL2 label code and return positioned findings with severity as JSON. Checks the command set Labelixa implements from the TSPL2 manual — a clean result is not a guarantee that a specific printer accepts the job. Run this before tspl_preview; if you are not sure which language the code is, call language_detect first.
输入模式
{
"type": "object",
"properties": {
"tspl": {
"type": "string",
"description": "Raw TSPL/TSPL2 code"
}
},
"required": [
"tspl"
]
}输出模式
{
"type": "object",
"properties": {
"diagnostics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Stable diagnostic code, e.g. ZPL0002"
},
"severity": {
"type": "string",
"enum": [
"error",
"warning",
"info"
]
},
"message_key": {
"type": "string",
"description": "i18n key for the message"
},
"mesaj": {
"type": "string",
"description": "Human-readable message in the requested language"
},
"line": {
"type": "integer"
},
"col": {
"type": "integer"
},
"end_line": {
"type": "integer"
},
"end_col": {
"type": "integer"
}
},
"required": [
"code",
"severity",
"line",
"col"
]
}
},
"ozet": {
"type": "object",
"properties": {
"toplam": {
"type": "integer"
},
"error": {
"type": "integer"
},
"warning": {
"type": "integer"
},
"info": {
"type": "integer"
}
},
"required": [
"toplam",
"error",
"warning",
"info"
]
}
},
"required": [
"diagnostics",
"ozet"
]
}🟢cpcl_validate(cpcl)
Lint CPCL label code and return positioned findings with severity as JSON. Checks the command set Labelixa implements from the CPCL manual — a clean result is not a guarantee that a specific printer accepts the job. Run this before cpcl_preview; if you are not sure which language the code is, call language_detect first.
输入模式
{
"type": "object",
"properties": {
"cpcl": {
"type": "string",
"description": "Raw CPCL code"
}
},
"required": [
"cpcl"
]
}输出模式
{
"type": "object",
"properties": {
"diagnostics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Stable diagnostic code, e.g. ZPL0002"
},
"severity": {
"type": "string",
"enum": [
"error",
"warning",
"info"
]
},
"message_key": {
"type": "string",
"description": "i18n key for the message"
},
"mesaj": {
"type": "string",
"description": "Human-readable message in the requested language"
},
"line": {
"type": "integer"
},
"col": {
"type": "integer"
},
"end_line": {
"type": "integer"
},
"end_col": {
"type": "integer"
}
},
"required": [
"code",
"severity",
"line",
"col"
]
}
},
"ozet": {
"type": "object",
"properties": {
"toplam": {
"type": "integer"
},
"error": {
"type": "integer"
},
"warning": {
"type": "integer"
},
"info": {
"type": "integer"
}
},
"required": [
"toplam",
"error",
"warning",
"info"
]
}
},
"required": [
"diagnostics",
"ozet"
]
}🟢explain_zpl(zpl, dpmm, width_in, height_in)
Full health report for a ZPL label: sectioned findings (syntax, size/DPI, orientation, barcodes, fonts, graphics memory, job behaviour) with an honest score — sections that cannot be assessed say so and are excluded from the score.
输入模式
{
"type": "object",
"properties": {
"zpl": {
"type": "string",
"description": "Raw ZPL code"
},
"dpmm": {
"type": "integer",
"enum": [
6,
8,
12,
24
],
"default": 8,
"description": "Printer density (8 = 203 dpi). The size/DPI section is scored against it — pass the real value."
},
"width_in": {
"type": "number",
"default": 4,
"description": "Label width in inches; fields outside it are reported."
},
"height_in": {
"type": "number",
"default": 6,
"description": "Label height in inches; same role as width_in."
}
},
"required": [
"zpl"
]
}🟢convert_zpl_dpi(zpl, source_dpi, target_dpi)
Rescale ZPL between printer resolutions (203/300/600 DPI): coordinates, fonts, barcode module width and label size are scaled. Embedded ^GF/~DG image data is NOT scaled; the response says so instead of silently passing it through.
输入模式
{
"type": "object",
"properties": {
"zpl": {
"type": "string",
"description": "Raw ZPL code"
},
"source_dpi": {
"type": "integer",
"enum": [
152,
203,
300,
600
],
"description": "Resolution the ZPL was written for, in DPI (not dpmm: 203 DPI = 8 dpmm)."
},
"target_dpi": {
"type": "integer",
"enum": [
152,
203,
300,
600
],
"description": "Resolution to rescale to, in DPI. Equal to source_dpi means no scaling."
}
},
"required": [
"zpl",
"source_dpi",
"target_dpi"
]
}🟢template_list(category, search)
List Labelixa's first-party label template catalog: id, English name, category, size/density and tags. Read-only product content (no tenant data). Fetch one with template_get; render its ZPL with zpl_preview.
输入模式
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"kargo",
"urun",
"raf",
"palet",
"qr"
],
"description": "Filter by category"
},
"search": {
"type": "string",
"description": "Substring match on id/tags"
}
}
}🟢template_get(template_id)
Fetch one catalog template: metadata, preview image URL and — for non-premium templates — the ZPL source, ready for zpl_preview. Premium templates return metadata for everyone; their ZPL source requires an API key whose plan includes the premium-template feature (same rule as the website).
输入模式
{
"type": "object",
"properties": {
"template_id": {
"type": "string",
"description": "Template id from template_list"
}
},
"required": [
"template_id"
]
}🟢epl_preview(epl, index)
Render EPL/EPL2 label code and return a PNG preview. The preview assumes 203 dpi and is an interpretation of the EPL2 manual covering a core command subset — no physical printer validation. `labels` in the response is the TOTAL number of labels the stream prints (a stream may contain several, each ended by `P`); pass `index` to render a different one.
输入模式
{
"type": "object",
"properties": {
"epl": {
"type": "string",
"description": "Raw EPL/EPL2 code"
},
"index": {
"type": "integer",
"default": 0,
"description": "Label index in the stream"
}
},
"required": [
"epl"
]
}🟢tspl_preview(tspl, index)
Render TSPL/TSPL2 label code and return a PNG preview. The preview assumes 203 dpi and is an interpretation of the TSPL manual covering a core command subset — no physical printer validation. `labels` in the response is the TOTAL number of labels the stream prints (a stream may contain several, each ended by `PRINT`); pass `index` to render a different one.
输入模式
{
"type": "object",
"properties": {
"tspl": {
"type": "string",
"description": "Raw TSPL/TSPL2 code"
},
"index": {
"type": "integer",
"default": 0,
"description": "Label index in the stream"
}
},
"required": [
"tspl"
]
}🟢cpcl_preview(cpcl, index)
Render CPCL label code and return a PNG preview. The preview assumes 203 dpi and is an interpretation of the CPCL manual covering a core command subset — no physical printer validation. `labels` in the response is the TOTAL number of labels the stream prints (a stream may contain several, each ended by `PRINT`); pass `index` to render a different one.
输入模式
{
"type": "object",
"properties": {
"cpcl": {
"type": "string",
"description": "Raw CPCL code"
},
"index": {
"type": "integer",
"default": 0,
"description": "Label index in the stream"
}
},
"required": [
"cpcl"
]
}🟢image_to_zpl(image_base64, dpmm, wrap, dither)
Convert an image (PNG, JPEG, BMP or GIF, max 200 KB) to a ZPL ^GF graphic command. Returns the ZPL plus measured dimensions and the physical print size at the chosen density. PDF input is REST-only (/v1/graphics).
输入模式
{
"type": "object",
"properties": {
"image_base64": {
"type": "string",
"description": "Base64-encoded image bytes"
},
"dpmm": {
"type": "integer",
"enum": [
6,
8,
12,
24
],
"default": 8,
"description": "Target printer density"
},
"wrap": {
"type": "boolean",
"default": false,
"description": "Wrap the ^GF in a printable ^XA...^XZ label with ^PW/^LL"
},
"dither": {
"type": "boolean",
"default": false,
"description": "Dither instead of hard threshold (photos)"
}
},
"required": [
"image_base64"
]
}🟢barcode_verify(image_base64)
Decode barcodes from a photo or scan of a PRINTED label (PNG, JPEG, BMP or GIF) and report what a software decoder reads back. Honest by design: 'read' does not guarantee every handheld scanner will read it, and 'not read' does not condemn the label (photo angle/focus matter) — the response says so.
输入模式
{
"type": "object",
"properties": {
"image_base64": {
"type": "string",
"description": "Base64-encoded image bytes"
}
},
"required": [
"image_base64"
]
}🟢zpl_compatibility(zpl, model)
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 and size-rule findings.
输入模式
{
"type": "object",
"properties": {
"zpl": {
"type": "string",
"description": "Raw ZPL code"
},
"model": {
"type": "string",
"description": "Printer model slug, manufacturer/model, e.g. zebra/zd421"
}
},
"required": [
"zpl",
"model"
]
}🟡bulk_submit(zpl, rows, output, dpmm, width_in, ...)
Submit a bulk label production job: one ZPL template with {{variable}} placeholders plus data rows (one object per label). Requires an API key whose plan includes bulk jobs. Quota is charged UPFRONT, one operation per row, and failed rows are not refunded; rows per job are capped by plan. Returns the job id — check bulk_status (small jobs usually finish within seconds).
输入模式
{
"type": "object",
"properties": {
"zpl": {
"type": "string",
"description": "ZPL template with {{name}} placeholders"
},
"rows": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"description": "One object per label: placeholder name -> value"
},
"output": {
"type": "string",
"enum": [
"zpl",
"png",
"pdf"
],
"description": "Output format (default zpl)"
},
"dpmm": {
"type": "integer",
"enum": [
6,
8,
12,
24
],
"description": "Print density (default 8)"
},
"width_in": {
"type": "number",
"description": "Label width, inches"
},
"height_in": {
"type": "number",
"description": "Label height, inches"
}
},
"required": [
"zpl",
"rows"
]
}🟢bulk_status(job_id)
Status of one bulk job you own: state, attempt count and — when finished — the summary with produced count and per-row failures (row number + reason; failed rows never block the rest). Finished outputs stay downloadable for 7 days via the REST endpoint the response names.
输入模式
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"description": "Job id from bulk_submit"
}
},
"required": [
"job_id"
]
}🟢bulk_list(limit)
List your recent bulk jobs (id, state, error class, timestamps), newest first. Useful to recover a lost job id; details via bulk_status.
输入模式
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Max jobs to return (default 50)"
}
}
}社区
证据