mcp_ocr
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PADDLEOCR_VL_BIN | No | Path to paddleocr-vl CLI binary | paddleocr-vl |
| PADDLEOCR_VL_TIMEOUT | No | Timeout in seconds for PaddleOCR-VL | 120 |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ocr_text_visionB | Extract text from an image. Returns full text, per-line confidence, and bounding boxes. Backend: vision. Apple Vision OCR — fast on-device GPU/ANE inference (macOS 10.15+). Best for CJK + major European languages. Zero install on macOS. |
| ocr_layout_visionB | Extract text with layout analysis. Returns blocks with bounding boxes. Backend: vision. Apple Vision OCR — fast on-device GPU/ANE inference (macOS 10.15+). Best for CJK + major European languages. Zero install on macOS. |
| ocr_table_visionB | Extract tables from an image. Returns structured CSV/JSON. Backend: vision. Apple Vision OCR — fast on-device GPU/ANE inference (macOS 10.15+). Best for CJK + major European languages. Zero install on macOS. |
| ocr_batch_visionB | OCR multiple images at once. Returns consolidated results. Backend: vision. Apple Vision OCR — fast on-device GPU/ANE inference (macOS 10.15+). Best for CJK + major European languages. Zero install on macOS. |
| ocr_text_paddleB | Extract text from an image. Returns full text, per-line confidence, and bounding boxes. Backend: paddle. PaddleOCR CPU — cross-platform, mature model. Wider language support than Vision, but slower. Requires PaddleOCR Python package. |
| ocr_layout_paddleB | Extract text with layout analysis. Returns blocks with bounding boxes. Backend: paddle. PaddleOCR CPU — cross-platform, mature model. Wider language support than Vision, but slower. Requires PaddleOCR Python package. |
| ocr_table_paddleB | Extract tables from an image. Returns structured CSV/JSON. Backend: paddle. PaddleOCR CPU — cross-platform, mature model. Wider language support than Vision, but slower. Requires PaddleOCR Python package. |
| ocr_batch_paddleB | OCR multiple images at once. Returns consolidated results. Backend: paddle. PaddleOCR CPU — cross-platform, mature model. Wider language support than Vision, but slower. Requires PaddleOCR Python package. |
| ocr_text_xiaomiB | Extract text from an image. Returns full text, per-line confidence, and bounding boxes. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
| ocr_layout_xiaomiA | Extract text with layout analysis. Returns blocks with bounding boxes. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
| ocr_table_xiaomiB | Extract tables from an image. Returns structured CSV/JSON. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
| ocr_formula_xiaomiA | Extract mathematical formulas from an image. Returns LaTeX. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
| ocr_document_xiaomiB | Parse a document image into Markdown: tables become HTML tables, formulas stay LaTeX, reading order preserved. Returns {'markdown': ...}. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
| ocr_kie_xiaomiA | Extract key information from a document image as a JSON object. Pass 'fields' (list of names) to narrow the output schema. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
| ocr_batch_xiaomiB | OCR multiple images at once. Returns consolidated results. Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak. |
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 15 tools
Names encode both capability and backend (ocr_{capability}_{backend}), so an agent can distinguish 'table' from 'layout' from 'text' tasks and see the backend choice explicitly. The main ambiguity is intentional duplication: ocr_text_vision, ocr_text_paddle and ocr_text_xiaomi do the same job, and choosing between them requires reading descriptions (speed vs language vs installation). Within the xiaomi family, ocr_layout_xiaomi, ocr_document_xiaomi and ocr_kie_xiaomi overlap in structured-output scope, though the descriptions do draw the lines.
A strict, predictable ocr_<capability>_<backend> pattern consistently applied across all 15 tools, with occasional longer capability names (document, formula, kie) that still read naturally. No mixing of camelCase, no stray verb styles, and the backend suffix lets an agent infer an entire tool family from one name.
15 tools is near the top of a comfortable range, but the count is explained by a sensible capability × backend matrix rather than ad-hoc sprawl. It is slightly heavy because each capability is triplicated across three backends, which could have been a single backend parameter; still, each tool corresponds to a real, distinct invocation.
Covers the core OCR surface well: plain text, layout blocks, tables, formulas, full-document Markdown, key-information extraction, and batch processing across three backends. Gaps are minor but notable: no capability/backend discovery tool (an agent cannot check which backends are installed or supported), and features like formula/document/KIE exist only under the xiaomi backend, so workflow coverage is uneven across backends.