VisionPower
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISIONPOWER_CACHE | No | 是否启用进程内结果缓存,默认 true。 | true |
| VISIONPOWER_DEBUG | No | 设为 true 时向 stderr 输出调试信息,默认 false。 | false |
| VISIONPOWER_MODEL | No | 视觉模型名称,默认 qwen3-vl-flash。 | qwen3-vl-flash |
| VISIONPOWER_CONFIG | No | 配置文件路径,默认 ~/.visionpower/config.json。 | ~/.visionpower/config.json |
| VISIONPOWER_API_KEY | Yes | 视觉模型服务商的 API Key。必填。也可回退读取 OPENAI_API_KEY。 | |
| VISIONPOWER_BASE_URL | No | OpenAI-compatible Base URL,不要包含 /chat/completions。默认 https://dashscope.aliyuncs.com/compatible-mode/v1。 | https://dashscope.aliyuncs.com/compatible-mode/v1 |
| VISIONPOWER_MAX_IMAGES | No | 单次调用最多分析的图片数量,默认 8。 | 8 |
| VISIONPOWER_MAX_TOKENS | No | 最大输出 token 数,默认 2048。 | 2048 |
| VISIONPOWER_TIMEOUT_MS | No | 上游接口超时时间(毫秒),默认 60000。 | 60000 |
| VISIONPOWER_MAX_RETRIES | No | 上游 429/5xx 或网络错误时的自动重试次数(指数退避 + 抖动),默认 2。 | 2 |
| VISIONPOWER_SKILL_STATE | No | 仅 Skill 脚本使用:记录配置是否已成功验证,默认 ~/.visionpower/skill-state.json。 | ~/.visionpower/skill-state.json |
| VISIONPOWER_ALLOWED_DIRS | No | 逗号分隔的允许目录白名单,image_path 必须落在其中。默认为空(不限制)。 | |
| VISIONPOWER_CACHE_TTL_MS | No | 单条缓存的存活时间(毫秒),默认 1800000 (30 分钟)。 | 1800000 |
| VISIONPOWER_MAX_IMAGE_BYTES | No | 单张本地/Base64 图片最大字节数,默认 20971520 (20MB)。 | 20971520 |
| VISIONPOWER_CACHE_MAX_ENTRIES | No | 结果缓存最多保留的条数,默认 32。设为 0 等同关闭缓存。 | 32 |
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 | Analyze one or more images with an OpenAI-compatible vision model. Supports local image_path, image_url, image_base64, or ordered images[]. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/helalove0812-source/visionpro-suite'
If you have feedback or need assistance with the MCP directory API, please join our Discord server