Schema | llm-vision-mcp

llm-vision-mcp

Overview Schema Related Servers Score Discussions

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`VISION_MODEL`	No	Model id passed to the provider.	mimo-v2.5
`VISION_PROVIDER`	No	Provider to use: openai, anthropic, or gemini. Defaults to openai.	openai
`VISION_CACHE_DIR`	No	On-disk image cache directory. If unset, memory-only caching is used.
`VISION_MAX_TOKENS`	No	Vision model output cap.	2048
`VISION_TIMEOUT_MS`	No	Fetch + provider timeout in milliseconds.	60000
`VISION_GEMINI_API_KEY`	No	Google AI Studio key. Required when VISION_PROVIDER is 'gemini'.
`VISION_OPENAI_API_KEY`	No	Key for the OpenAI-compatible endpoint. Required when VISION_PROVIDER is 'openai' (the default).
`VISION_GEMINI_BASE_URL`	No	Gemini base URL.	https://generativelanguage.googleapis.com
`VISION_OPENAI_BASE_URL`	No	Base URL for OpenAI-compatible endpoint (OpenRouter / gateway / opencode GO).	https://api.openai.com/v1
`VISION_ANTHROPIC_API_KEY`	No	Anthropic API key. Required when VISION_PROVIDER is 'anthropic'.
`VISION_ANTHROPIC_BASE_URL`	No	Anthropic base URL.	https://api.anthropic.com
`VISION_BLOCK_PRIVATE_URLS`	No	Set to 'true' to block localhost/private URL fetches.	false

Capabilities

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }

Tools

Functions exposed to the LLM to take actions

Name Description

Name	Description
analyze_imageA	Analyze an image using a multimodal model and return a detailed text description. The vision model sees the image; the calling agent is text-only and cannot. Sources for `image` (pick one): "path": absolute or relative path to a local image file (PNG/JPEG/WEBP/GIF) URL: http(s) URL to an image on the web or a local server "data:...": base64 data URI, e.g. data:image/png;base64, "clipboard": read the image currently copied to the system clipboard "raw": the string itself is the literal raw image bytes Pick `task` for common jobs (describe \| ocr \| ui \| layout \| qa) or pass your own `prompt`. `detail` defaults to "high" for maximum completeness. Use `save_to` to write a long description to a file and get back only a path + summary.

analyze_imageA

Analyze an image using a multimodal model and return a detailed text description. The vision model sees the image; the calling agent is text-only and cannot.

Sources for image (pick one):

"path": absolute or relative path to a local image file (PNG/JPEG/WEBP/GIF)
URL: http(s) URL to an image on the web or a local server
"data:...": base64 data URI, e.g. data:image/png;base64,
"clipboard": read the image currently copied to the system clipboard
"raw": the string itself is the literal raw image bytes

Pick task for common jobs (describe | ocr | ui | layout | qa) or pass your own prompt. detail defaults to "high" for maximum completeness. Use save_to to write a long description to a file and get back only a path + summary.

Prompts

Interactive templates invoked by user choice

Name	Description
No prompts

Resources

Contextual data attached and managed by the client

Name	Description
No resources

Server Configuration
Capabilities
Tools
Prompts
Resources

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/KuaaMU/llm-vision-mcp'

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