vision-mcp
by sulghu
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | No | Model name to use for vision tasks. | qwen3.7-plus |
| OPENAI_API_KEY | No | OpenAI API key. Alternative to VISION_API_KEY. | |
| VISION_API_KEY | No | API key for your vision model provider. If not set, DASHSCOPE_API_KEY or OPENAI_API_KEY can be used. | |
| VISION_TIMEOUT | No | Timeout in milliseconds for API requests. | 120000 |
| VISION_BASE_URL | No | Base URL for an OpenAI-compatible vision endpoint. | https://dashscope.aliyuncs.com/compatible-mode/v1 |
| DASHSCOPE_API_KEY | No | Alibaba Cloud DashScope API key. Alternative to VISION_API_KEY. | |
| VISION_MAX_TOKENS | No | Maximum number of tokens in the response. | 1024 |
| VISION_ENABLE_THINKING | No | Whether to enable thinking mode for qwen3 models (true/false). | false |
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
ActivitySlowing
ResponsivenessNo issues