vision-router-mcp
Server Configuration
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 |
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 | {
"listChanged": true
} |
Tools
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。 |
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 4 tools
Each tool serves a clearly distinct purpose: listing configurations, providing setup guidance, analyzing images, and testing connections. No two tools overlap in functionality, so an agent can easily select the right one.
All tools share the 'vision_' prefix and generally follow a verb_noun pattern (list_models, get_setup_guide, test_connection). 'vision_analyze' is slightly inconsistent as it lacks a noun, but the pattern is still highly predictable and readable.
With 4 tools, the server is tightly scoped to the vision-routing domain. Each tool is essential and there are no redundant or unnecessary additions.
The tool surface covers the full lifecycle for a vision router: discovering available models, understanding setup, testing connectivity, and performing analysis. No obvious gaps exist for the stated purpose.