Local Eyes
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Ollama host URL. | http://localhost:11434 |
| GEMINI_MODEL | No | Gemini model to use when `LOCAL_EYES_BACKEND=gemini`. | gemma-4-31b-it |
| OLLAMA_MODEL | No | Any Ollama vision model. | gemma4:e4b |
| GEMINI_API_KEY | No | Required for the `gemini` backend. | |
| LOCAL_EYES_ROOT | No | If set, local paths must be inside this folder. | |
| LOCAL_EYES_CACHE | No | Set to `1` to enable the replay cache (same as `--cache`). | off |
| LOCAL_EYES_BACKEND | No | Backend to use: `ollama` or `gemini`. | ollama |
| LOCAL_EYES_MAX_SIDE | No | Images are downscaled to this maximum side length before sending. | 1600 |
| LOCAL_EYES_CACHE_DIR | No | Directory used for cached validated responses. | ./cache |
| LOCAL_EYES_ALLOW_PRIVATE_URLS | No | URLs to localhost/private networks are refused by default. | off |
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 |
|---|---|
| describe_imageB | Describe an image, or answer a question about it. path_or_url: absolute local path or http(s) URL. |
| extract_textB | OCR: return all visible text verbatim, plus any error/warning messages shown (great for UI screenshots). |
| read_uiB | Read a UI screenshot: structured elements (type, label, value, state), visible errors, and layout issues. |
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 3 tools
The three tools carve out reasonably distinct niches: free-form description/Q&A, verbatim OCR, and structured UI element extraction. The main friction is that extract_text is explicitly pitched at UI screenshots, overlapping with read_ui, and describe_image's open-ended 'answer a question' scope can subsume either of the others.
All three names follow a clean verb_noun snake_case pattern (describe_image, extract_text, read_ui), with the verb matching the action and the noun matching the input/artifact.
Three tools is on the lean side but well-matched to a narrow image-inspection domain, with each tool earning its place. It sits just above the 'thin' threshold and leaves little room for edge cases like metadata or region-specific reads.
The surface covers the core jobs of local image understanding: general description, text extraction, and structured UI parsing, with clear input handling via path or URL. Minor gaps exist for basic image metadata (dimensions/format) or comparing/reading a specific region, but agents can work around these.