Schema | vision-router-mcp

vision-router-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VISION_ROUTER_CONFIG`	No	配置文件路径，默认为平台默认目录
`VISION_ROUTER_CONFIG_DIR`	No	配置目录，默认为平台默认目录（Windows：%APPDATA%\vision-router-mcp）
`VISION_ROUTER_MAX_IMAGE_BYTES`	No	图片大小上限（字节）	10485760
`VISION_ROUTER_ALLOWED_IMAGE_ROOTS`	No	本地图片允许目录（;分隔），默认为MCP Server工作目录

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
vision_list_modelsA	列出所有视觉模型配置及其启用和 API Key 配置状态。不会返回 API Key。系统没有默认视觉模型，调用 vision_analyze 时必须明确指定 provider_id。
vision_analyzeA	使用用户明确指定的云端视觉模型分析一张图片。必须提供 provider_id，且必须且只能提供 image_url、image_base64、image_path 之一。不要在参数中传递 API Key。
vision_get_setup_guideA	返回视觉模型配置说明和推荐供应商。不会自动选择或启用任何模型。
vision_test_connectionA	测试某个已配置 provider 的连通性（Key/模型/端点）。默认只检查配置；perform_request=true 时发送最小文本请求验证认证。不会接收 API Key。

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/wotonger/vision-router-mcp'

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