Schema | MCP Vision Server

MCP Vision Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`GROQ_API_KEY`	No	Groq API Key
`VISION_MODEL`	No	视觉理解模型（用于 analyze_image, extract_text）
`AGNES_API_KEY`	No	Agnes AI API Key
`AGNES_TIMEOUT`	No	Agnes AI 超时时间（秒）	120
`AGNES_BASE_URL`	No	Agnes AI 基础 URL	https://apihub.agnes-ai.com/v1
`CUSTOM_API_KEY`	No	自定义端点 API Key
`IMAGE_PROVIDER`	No	图片任务专用 Provider	跟随 VISION_PROVIDER
`OPENAI_API_KEY`	No	OpenAI API Key
`VIDEO_PROVIDER`	No	视频任务专用 Provider	跟随 VISION_PROVIDER
`CUSTOM_BASE_URL`	No	自定义端点地址
`IMAGE_GEN_MODEL`	No	文生图模型（用于 generate_image）
`VIDEO_GEN_MODEL`	No	视频生成模型（用于 generate_video）
`VISION_PROVIDER`	No	默认 Provider 名称，可选值：agnes, openai, openrouter, groq, custom	auto-detected
`IMAGE_EDIT_MODEL`	No	图片编辑模型（用于 edit_image）
`AGNES_MAX_RETRIES`	No	Agnes AI 最大重试次数	3
`PROVIDER_FALLBACK`	No	备选 Provider 列表，逗号分隔
`OPENROUTER_API_KEY`	No	OpenRouter API Key
`AGNES_DEFAULT_MODEL`	No	Agnes AI 默认模型	agnes-2.0-flash
`VIDEO_ANALYSIS_MODEL`	No	视频分析模型（用于 analyze_video）

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rosecat2359/mcp-vision-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server