DeepSeek Eyes
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSEEK_EYES_API_KEY | Yes | API key for the vision model provider (default: Alibaba Cloud Bailian). | |
| DEEPSEEK_EYES_THINKING | No | Set to '1' to enable thinking mode for the vision model, otherwise defaults to disabled. | 0 |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| describe_imageA | 识别一张图片并返回文字描述。图片可来自本地文件路径、网络 URL(http/https) 或 data URL。 |
| describe_images_in_folderA | 扫描一个文件夹中的所有图片，并行识别并返回每张图片的描述。适用于一次识别多张图片（例如把多张截图放进一个文件夹后批量分析）。并行识别，速度较快。 |
| describe_pasted_imagesA | 从会话记录中提取用户最近一次粘贴或上传的图片（单张或多张均可），并行识别并返回每张的描述。适用于对话里图片显示为 [Unsupported Image] 的场景——以用户真正上传到输入框的图片为准，不受剪贴板影响。只处理最近一条含图片的用户消息，避免混入历史图片。 |
| get_configA | 查看当前识图配置：提供商、模型、Base URL、API Key 是否已设置。不返回明文 Key。 |
| update_configA | 修改识图配置并持久化到 ~/.deepseek-eyes/config.json。API Key 不写入文件，请通过环境变量 DEEPSEEK_EYES_API_KEY 提供。 |
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 5 tools
Each tool has a clearly distinct purpose: three describe images from different sources (single input, folder, pasted conversation images), and two manage configuration. No overlapping or ambiguous boundaries.
All tool names follow a consistent verb_noun pattern: describe_* for image actions and get_config/update_config for configuration. Naming is uniform and predictable.
With 5 tools, the server is well-scoped for its purpose: 3 image description methods plus 2 config operations. Each tool earns its place without bloat or thinness.
The surface covers all necessary operations for an image description server: single, batch folder, and pasted image inputs, plus config viewing/updating. No obvious gaps or dead ends.