Schema | mcp-image-analyzer

mcp-image-analyzer

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OPENAI_MODEL`	Yes	Default model to use for image analysis, e.g., qwen-vl-max.
`OPENAI_API_KEY`	Yes	API key for the OpenAI-compatible service.
`OPENAI_BASE_URL`	Yes	Base URL of the OpenAI-compatible API endpoint, without /v1 suffix.
`OPENAI_API_VERSION`	No	API version path segment. Use 'v1' for OpenAI/DashScope, 'v4' for Zhipu.	v1
`IMAGE_ANALYZER_MAX_TOKENS`	No	Maximum number of tokens in the output.	1024
`IMAGE_ANALYZER_TIMEOUT_MS`	No	Timeout in milliseconds for each API request.	60000
`IMAGE_ANALYZER_SEND_DETAIL`	No	Whether to send 'detail' parameter. Only for official OpenAI endpoints.	0
`IMAGE_ANALYZER_MAX_IMAGE_MB`	No	Maximum image file size in megabytes.	20
`IMAGE_ANALYZER_COMPRESS_MAX_EDGE`	No	Maximum edge length in pixels when compressing.	2048
`IMAGE_ANALYZER_COMPRESS_THRESHOLD`	No	Compress image if decoded size exceeds this many bytes.	1500000

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
analyze_imageA	使用多模态模型分析图片内容。支持本地文件路径、Base64 编码、或图片 URL。可用于识别图中文字、物体、场景、图表等。

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/yunper-wang/mcp-image-analyzer'

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