Schema | visual-intelligence-mcp

visual-intelligence-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VI_MODEL`	No	Model name (must support vision). Default: minimax-m3.	minimax-m3
`VI_API_KEY`	Yes	Middleware API key (required).
`VI_BASE_URL`	Yes	Middleware base URL, e.g., https://api.xxx.com/v1 (required).
`VI_MAX_TOKENS`	No	Maximum response tokens. Default: 2048.	2048
`VI_IMAGE_QUALITY`	No	JPEG quality (1-100). Default: 80.	80
`VI_MAX_IMAGE_SIZE`	No	Max image width/height in pixels; larger images are scaled down. Default: 1280.	1280
`VI_MAX_IMAGE_BYTES`	No	Max compressed image size; errors if exceeded. Default: 10MB.	10MB
`VI_REQUEST_TIMEOUT_MS`	No	Request timeout in milliseconds. Default: 60000.	60000

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
analyze_imageA	分析本地图片(UI 自动化视觉辅助)。当需要"查看屏幕/截图/界面"时使用:传入截图路径与问题,返回多模态模型的文字描述或结构化 JSON。调用规范(必须遵守): 调用前,先在回复中说明你正在分析哪张截图及其目的(如"让我分析一下当前界面")。 prompt 必须写明具体想知道的描述内容,例如 "描述界面布局并列出所有可见按钮"、"截图中有哪些错误提示"、"这个弹窗的标题和选项是什么"。禁止传空 prompt 或含糊 prompt(如 "看一下"、"描述" ),server 会把过短的 prompt 视为无效并自动补充标准描述要求。图片必须已保存为本地文件,传入绝对路径;本工具自行读取,无需传图片内容。需要结构化结果(如元素坐标)时设置 json_mode=true,要求模型返回 JSON。

Name

Description

分析本地图片(UI 自动化视觉辅助)。

当需要"查看屏幕/截图/界面"时使用:传入截图路径与问题,返回多模态模型的文字描述或结构化 JSON。

调用规范(必须遵守):

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/KOG123/visual-intelligence-mcp'

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