opencode-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | No | Primary vision model. Default: google/gemma-4-31b-it. | google/gemma-4-31b-it |
| OPENROUTER_API_KEY | Yes | Required. OpenRouter API key. | |
| VISION_FALLBACK_MODEL | No | Fallback vision model. Default: qwen/qwen3-vl-32b-instruct. | qwen/qwen3-vl-32b-instruct |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_imageA | Анализирует изображение: распознаёт текст, объекты, сцены. Принимает путь к файлу и опциональный вопрос. |
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 1 tool
With only one tool, there is no ambiguity between tools. The purpose is clear and distinct.
A single tool name follows a clear verb_noun pattern (read_image) and there is no inconsistency.
The server has a single tool, which feels thin for a vision-oriented server. While it can handle multiple tasks within one tool, the scope suggests more tools would be expected for a complete set.
The single tool covers text, object, and scene recognition with optional questions, but lacks other common operations like listing images, generating descriptions, or handling multiple images in batch. There are moderate gaps for typical vision use cases.