Skip to main content
Glama
KuaaMU

llm-vision-mcp

by KuaaMU
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VISION_MODELNoModel id passed to the provider.mimo-v2.5
VISION_PROVIDERNoProvider to use: openai, anthropic, or gemini. Defaults to openai.openai
VISION_CACHE_DIRNoOn-disk image cache directory. If unset, memory-only caching is used.
VISION_MAX_TOKENSNoVision model output cap.2048
VISION_TIMEOUT_MSNoFetch + provider timeout in milliseconds.60000
VISION_GEMINI_API_KEYNoGoogle AI Studio key. Required when VISION_PROVIDER is 'gemini'.
VISION_OPENAI_API_KEYNoKey for the OpenAI-compatible endpoint. Required when VISION_PROVIDER is 'openai' (the default).
VISION_GEMINI_BASE_URLNoGemini base URL.https://generativelanguage.googleapis.com
VISION_OPENAI_BASE_URLNoBase URL for OpenAI-compatible endpoint (OpenRouter / gateway / opencode GO).https://api.openai.com/v1
VISION_ANTHROPIC_API_KEYNoAnthropic API key. Required when VISION_PROVIDER is 'anthropic'.
VISION_ANTHROPIC_BASE_URLNoAnthropic base URL.https://api.anthropic.com
VISION_BLOCK_PRIVATE_URLSNoSet to 'true' to block localhost/private URL fetches.false

Instructions

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.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

  • "recent": auto-find the most recently pasted image (scans Codex attachments, Grok session images, Claude transcripts)

  • "session": auto-find images pasted in this session

  • "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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.7/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap. The single tool has a clear and distinct purpose: analyzing images.

Naming Consistency5/5

The tool name 'analyze_image' follows a clean verb_noun pattern. Since there is only one tool, naming consistency is perfect.

Tool Count4/5

The server has exactly one tool, which feels slightly thin but is reasonable for a highly focused vision analysis server. The tool is comprehensive, handling many tasks through parameters, so the count is not inadequate.

Completeness5/5

The tool covers a wide range of vision tasks including describe, OCR, UI, layout, and QA, with multiple input sources and output options. There are no obvious gaps for the stated purpose of enabling text-only agents to analyze images.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources