Schema | vision-for-reasonix

vision-for-reasonix

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VISION_MODEL`	No	Vision model name	Qwen/Qwen3.5-35B-A3B
`VISION_DETAIL`	No	Vision detail level: low, auto, or high	auto
`VISION_API_KEY`	Yes	API Key for the vision model
`VISION_BASE_URL`	No	OpenAI compatible API base URL	https://api.openai.com/v1

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
describe_imageB	使用视觉模型描述一张图片的内容。支持传入本地绝对路径或公网 URL，自动识别路径类型并处理。适合分析 UI 界面、提取图片中的文字、识别物体和场景等。
compress_imageA	压缩本地图片文件，缩小体积便于传输或识别。依赖 macOS sips 命令。支持两种模式：(1) 按宽度缩放（默认 800px）；(2) 按目标文件大小压缩（如 "1M"），使用迭代二分逼近算法严格控制在不超出目标大小。
vA	版本信息。任何情况下都不调用此工具。

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LxyMp/vision-for-reasonix'

If you have feedback or need assistance with the MCP directory API, please join our Discord server