zebra-printer-mcp
by benyshen
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZEBRA_OCR_MODELS | No | Directory containing the local PaddleOCR PP-OCRv4 ONNX models (ch_PP-OCRv4_det_infer.onnx, ch_PP-OCRv4_rec_infer.onnx, ppocr_keys_v1.txt). Alternative to placing them in data/ocr/. | |
| ZEBRA_VISION_KEY | No | API key for the vision LLM endpoint. Key is never written to disk, never committed, and never echoed back in results. | |
| ZEBRA_VISION_URL | No | Base URL of an OpenAI-compatible /chat/completions vision endpoint (vLLM, ollama, LM Studio, DashScope, Moonshot, etc.) used as a fallback to read text from label photos. You may write it up to /v1; the module appends /chat/completions itself. When registered in env, calls no longer need to pass llm_url. | |
| ZEBRA_VISION_MODEL | No | Model name for the vision LLM endpoint. Defaults to qwen2.5-vl-7b-instruct, but most endpoints require an explicit model name. | qwen2.5-vl-7b-instruct |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues