Skip to main content
Glama
jmars
by jmars

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
ocr_imageA

OCR text from an image.

Extracts text using the best available OCR backend. Returns text blocks with confidence scores and bounding boxes.

Args: image_path: Absolute path to the image file (must be under home directory)

image_metadataA

Extract full metadata from an image.

Returns file info (size, timestamps, SHA-256), image properties (format, dimensions, DPI, colour space), and EXIF data including camera make/model, datetime, and GPS coordinates.

Args: path: Absolute path to the image file (must be under home directory)

extract_textA

Extract all text and metadata from an image.

Convenience wrapper that combines OCR text extraction with full image metadata in a single JSON response.

Args: image_path: Absolute path to the image file (must be under home directory)

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 3 tools

Disambiguation4/5

ocr_image and extract_text both handle text extraction, causing slight overlap, but extract_text explicitly combines OCR with metadata, making its broader purpose clear. image_metadata is distinct.

Naming Consistency3/5

Names mix conventions: ocr_image (verb_noun), image_metadata (noun_noun), and extract_text (verb_noun). The inconsistency is noticeable but still readable.

Tool Count5/5

Three tools is well-scoped for a focused image analysis server, though extract_text is somewhat redundant as a convenience wrapper.

Completeness4/5

The server covers OCR and metadata extraction, including a combined wrapper, but lacks broader image analysis features such as classification or object detection, which the server name might imply.

Maintenance

ActivityStale
ResponsivenessNo issues