Schema | vision-augment

vision-augment

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VISION_AUGMENT_HOST`	No	HTTP bind address	127.0.0.1
`VISION_AUGMENT_PORT`	No	HTTP port	8000
`VISION_AUGMENT_DEBUG`	No	DEBUG logging	false
`VISION_AUGMENT_CHANNELS`	No	OpenAI-compatible channel JSON array	[]
`VISION_AUGMENT_CACHE_DIR`	No	Cache directory	~/.cache/vision-augment
`VISION_AUGMENT_TRANSPORT`	No	Transport: stdio / streamable-http	stdio
`VISION_AUGMENT_ALLOW_URLS`	No	Allow http(s) input (SSRF prevention, default off)	false
`VISION_AUGMENT_OLLAMA_URL`	No	Local Ollama address	http://127.0.0.1:11434
`VISION_AUGMENT_MAX_INPUT_MB`	No	Input size limit	50
`VISION_AUGMENT_MAX_OUTPUT_CHARS`	No	Output truncation limit	20000
`VISION_AUGMENT_CACHE_TTL_SECONDS`	No	Cache TTL (0=disabled)	86400

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
mcp_vision_augment_visionA	多模态视觉工具：为无视觉能力的 LLM 提供看图、OCR 与文档解析能力。返回统一 JSON envelope：{task_type, tool_used, code, error, result, confidence, metadata}。视觉理解按配置的 OpenAI 兼容通道依次降级，最后兜底本地 Ollama VL 模型； OCR 与文档解析在本地完成（RapidOCR / markitdown）。
mcp_vision_augment_clear_cacheA	清除本地结果缓存（缓存 TTL 上限由 VISION_AUGMENT_CACHE_TTL_SECONDS 控制）。
mcp_vision_augment_healthA	环境探测：检查视觉通道/Ollama/OCR/文档引擎的配置状态（不含密钥），用于向用户反馈还缺少哪些配置及对应安装命令。

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/CaoMeiYouRen/vision-augment'

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