Local Vision
Verified IntegrationClient Configuration
— Connect Local Vision to Claude Desktop or Cursor in seconds{
"mcpServers": {
"local-vision": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-local-vision"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Converts local images into descriptive text using a local vision language model for integration with large language models lacking visual capabilities.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Local Vision
Yes, Local Vision is designed to integrate with large language models lacking visual capabilities, often via its MCP (Model Context Protocol) server. It uses local vision models (like those from LM Studio) to provide visual understanding to other AI systems.
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.