LLM Vision
Verified IntegrationClient Configuration
— Connect LLM Vision to Claude Desktop or Cursor in seconds{
"mcpServers": {
"llm-vision": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-llm-vision"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Integrates vision capabilities into any Large Language Model by routing image inputs through specialized vision models and returning text descriptions.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for LLM Vision
LLM Vision is an MCP server designed to integrate advanced vision capabilities into any Large Language Model. It processes various image inputs through specialized vision models and returns detailed text descriptions, allowing non-vision LLMs to understand visual content.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.