deepseek-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Model ID, default gemini-3.5-flash. | |
| GEMINI_API_KEY | Yes | Your Gemini API key, required. | |
| GEMINI_API_BASE | No | API endpoint, default https://generativelanguage.googleapis.com/v1beta |
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 |
|---|---|
| analyze_imageA | 调用 Gemini 视觉模型（默认模型 gemini-3.5-flash，可用环境变量 GEMINI_MODEL 覆盖）分析一张图片，返回模型的文本描述/回答。image 支持本地文件路径、http(s) 图片 URL 或 base64 data URI。 |
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 ambiguity or overlap. The tool's purpose is clearly defined.
With a single tool, the naming is trivially consistent. The verb_noun pattern (analyze_image) is clear and appropriate.
The server has only one tool, which is explicitly considered too few. Even for a narrowly scoped vision service, a single tool feels excessively thin.
For the apparent purpose of analyzing a single image, the tool fully covers the core need. Minor gaps like batch processing or model introspection exist but are not critical for the basic use case.