simple-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | Yes | Model name for vision. | gpt-4o-mini |
| VISION_RESIZE | No | Resize image before analysis (WxH format, e.g., 1920x1080). | |
| VISION_API_KEY | Yes | Your API key for the OpenAI-compatible vision API. | |
| VISION_TIMEOUT | No | Request timeout in seconds. | 120 |
| VISION_BASE_URL | Yes | API endpoint base URL. | https://api.openai.com/v1 |
| VISION_MAX_TOKENS | No | Max response tokens. | 4096 |
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 |
|---|---|
| analyze_imageB | Analyzes an image and returns a detailed description. Supports PNG, JPEG, GIF, WebP, and BMP formats. |
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; the single tool's purpose is clearly described.
The tool name 'analyze_image' follows a clear verb_noun pattern in snake_case, which is consistent and descriptive.
A single tool is insufficient for a meaningful vision server; typical vision tasks require multiple operations beyond just analysis.
Only one generalized analysis tool exists, lacking common vision capabilities like object detection, OCR, or image comparison.