Vision MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VLM_MODEL | No | Model name. | qwen2.5vl:3b |
| VLM_API_MODE | No | API format: ollama (native /api/chat, supports keep-alive) or openai (standard /v1/chat/completions, any OpenAI-compatible backend). | ollama |
| VLM_BASE_URL | No | Backend address. Defaults to http://localhost:11434 for ollama mode and http://localhost:11434/v1 for openai mode. Note: openai mode requires the /v1 suffix. | http://localhost:11434 |
| VLM_KEEP_ALIVE | No | Model residency in Ollama mode only. 0 unloads after each call, -1 keeps forever. | 30m |
| VLM_TIMEOUT_MS | No | Per-call timeout in milliseconds, covers cold-start model load. | 300000 |
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 |
|---|---|
| describe_imageA | 对一张或多张图片进行视觉理解（识图）：可指定任意问题，如描述内容、识别物体、分析图表、理解截图等 |
| ocr_imageA | 提取一张或多张图片中的所有文字（OCR），按原始排版分行输出 |
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 2 tools
The two tools have clear but slightly overlapping purposes: describe_image offers general visual understanding, while ocr_image specifically extracts text. An agent could theoretically use describe_image for text extraction, but the OCR tool is more direct and precise for that task.
Both tools follow a consistent verb_noun pattern (describe_image, ocr_image), making the tool names predictable and easy to select.
With only 2 tools, the server feels minimal, but it covers the essential tasks of visual understanding and OCR. It's borderline but not unreasonable for a purpose-built vision server.
The two tools cover the core needs of image understanding and text extraction, and describe_image is versatile enough to handle many query types. Minor gaps exist, such as no dedicated tools for image comparison or object detection, but these can be handled through describe_image.