Schema | Vision-Multi MCP Server

Vision-Multi MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VISION_MODEL`	No	默认后端模型	qwen3.7-flash
`VISION_PROVIDERS`	No	附加后端 JSON 数组
`DASHSCOPE_API_KEY`	No	默认后端 API key（至少需要一个后端）
`VISION_STATE_FILE`	No	状态文件路径	<REASONIX_HOME>/mcp-state/vision-multi-state.json
`DASHSCOPE_BASE_URL`	No	默认后端接口地址	https://dashscope.aliyuncs.com/compatible-mode/v1
`VISION_FAIL_THRESHOLD`	No	连续失败多少次后自动切换默认后端	1
`VISION_DEFAULT_PROVIDER`	No	默认后端 id（不传时按 apiKey 已配置的第一个后端）

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
analyze_imageA	使用视觉大模型分析图片内容。传入本地图片文件路径或 http(s) 图片 URL，可附带问题。可用 provider 参数手动切换识别后端（用 list_providers 查看），可用 model 参数覆盖该后端的默认模型。
list_providersA	列出当前配置的所有视觉识别后端（id / 名称 / 模型 / 接口地址），不含密钥。用于手动切换前查看可选后端。

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/snow930/reasonix-vision-multi'

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