mcp-vision
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_H2O_URL | No | URL of the H2O model service endpoint used for image decisions. | http://127.0.0.1:1237 |
| VISION_OCR_URL | No | URL of the OCR model service endpoint. | http://127.0.0.1:1239 |
| VISION_LIQUID_URL | No | URL of the Liquid model service endpoint used for image descriptions. | http://127.0.0.1:1246 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| image_ocrA | Read text and image-local bounding regions from an absolute local image path. query filters OCR text. Coordinates describe pixels, not desktop click targets. |
| image_describeA | Ask Liquid CPU vision a question about a local image file. Returns text; descriptions may be inaccurate. Use an absolute path. |
| image_decideA | Ask H2O a boolean, choice, or ordered-score question. Supply an absolute image path, text context, or both. Images require H2O vision enabled. Probabilities are model scores, not verified accuracy. |
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
image_ocr is clearly separate (text extraction), but image_describe and image_decide both reduce to 'ask a model a question about an image' and differ mainly by answer format and backend model (Liquid CPU vs H2O). The descriptions help, but an agent must parse subtle wording to choose between free-text description and constrained boolean/choice/score answers.
All three tools share a clean snake_case `image_` prefix, which makes them obviously part of one family. Minor deviation: `image_ocr` uses an acronym-noun while `image_describe`/`image_decide` use verbs, so the action pattern isn't perfectly uniform.
Three tools is on the thin side but each covers a genuinely different modality (OCR with regions, free-text description, constrained decision/scoring). Nothing feels redundant, though the surface is small for a general vision server.
Core read-only vision operations are covered, but there is no image metadata/info tool, no object/localization tool beyond OCR regions, no multi-image comparison, and no preprocessing (crop/resize) step. Agents can partially work around these via describe/decide, but several natural vision tasks are dead ends.