deepseek-mcp-image
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_IMAGE_BYTES | No | 单张图片大小上限，默认 20971520 (20MB) | 20971520 |
| SENSENOVA_API_KEY | Yes | 商汤 API Key | |
| SENSENOVA_BASE_URL | No | API 基础地址 | https://token.sensenova.cn/v1 |
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 |
|---|---|
| describe_imageA | 读取一张图片（本地文件路径或 http(s):// URL），调用多模态模型 SenseNova 6.8 Flash-Lite 识别其内容并返回文字描述。用于主模型不支持图片输入时的看图能力。 |
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 1 tool
Only one tool exists, so there is no possibility of confusing it with another tool. Its purpose is clearly defined as image description.
The tool name 'describe_image' follows a clear verb_noun pattern and accurately reflects its function.
The server is intentionally scoped to a single capability (image description), so one tool is the appropriate and complete set for its purpose.
The tool covers the entire domain it claims to serve: reading images from paths or URLs and returning descriptions. No additional operations are needed for this specific purpose.