vision-mcp
by Peter-Lpt
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | No | 视觉模型名 | qwen-vl-plus |
| VISION_API_KEY | No | 视觉后端 API Key (recommended, no default) | |
| VISION_TIMEOUT | No | 请求超时（秒） | 120 |
| MCP_SERVER_NAME | No | MCP server 名称 | vision-mcp |
| VISION_BASE_URL | No | OpenAI 兼容端点 | https://dashscope.aliyuncs.com/compatible-mode/v1 |
| VISION_MAX_TOKENS | No | 单次最大输出 token | 4096 |
| VISION_AUTO_RESIZE | No | 是否自动缩放图片 | true |
| VISION_MAX_IMAGE_BYTES | No | 单图大小上限（字节） | 20971520 |
| VISION_MAX_IMAGE_DIMENSION | No | 图片最大边长 px，超过自动缩小 | 4000 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues