OCR Beans
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ocr_pdfA | Extrai texto de um PDF. Detecta automaticamente fontes corrompidas (comum em PDFs judiciais brasileiros) e aplica OCR quando necessário. |
| ocr_pageA | Extrai texto de páginas específicas de um PDF. |
| ocr_imageA | Extrai texto de uma imagem via OCR (Tesseract). |
| check_legibilityA | Diagnóstico rápido: verifica se um PDF tem fontes corrompidas/proprietárias. |
| batch_ocrA | Processa todos os PDFs de um diretório via OCR. |
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 5 tools
Each tool has a fairly distinct target: ocr_image (images), check_legibility (diagnostic), batch_ocr (directory batch), ocr_pdf (full PDF), and ocr_page (specific pages). The only mild overlap is ocr_pdf vs ocr_page, but the descriptions clearly delineate the full-document vs page-subset use cases.
Three tools share the 'ocr_' prefix (ocr_image, ocr_pdf, ocr_page) and the rest use clear verb_noun forms (check_legibility, batch_ocr). Mostly readable and predictable, though the prefix/suffix placement of 'ocr' varies slightly.
Five tools is a tight, well-scoped set for an OCR/PDF extraction domain. Every tool covers a distinct entry point (single image, single PDF, page subset, batch directory, pre-flight diagnostic) with no redundancy.
The surface covers the core OCR lifecycle well: images, full PDFs, page subsets, batch directories, and a legibility diagnostic. Minor gaps remain (e.g. batch image processing or configurable output formats), but the main workflows are fully supported.