Schema | vision_mcp

vision_mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VISION_MODEL`	No	Vision model name.	qwen-vl-plus
`VISION_API_KEY`	No	API key for the vision model. Not needed for local deployments.	not-needed
`VISION_API_BASE`	No	API base URL for the vision model, without /chat/completions suffix.	http://localhost:8000/v1
`VISION_MAX_TOKENS`	No	Maximum output tokens per response.	2000

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.

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`	{}

Functions exposed to the LLM to take actions

Name	Description
vision_pingA	Diagnostic: return a test string to verify MCP communication.
describe_imageA	理解并描述图片内容。传入本地图片文件绝对路径，返回对该图片的详细文字描述。当用户让你查看、理解、分析或描述任何图片时，你必须调用此工具。支持 PNG、JPG、JPEG、GIF、WebP、BMP 等常见图片格式。

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/rongtianjie/vision_mcp'

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