Gimmick Vision
Verified IntegrationClient Configuration
— Connect Gimmick Vision to Claude Desktop or Cursor in seconds{
"mcpServers": {
"gimmick-vision": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gimmick-vision"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Bridges AI agents like Claude Code to any local OpenAI-compatible vision model for image analysis.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Gimmick Vision
It is compatible with any local vision model server that exposes an OpenAI-compatible API, including popular options like llama.cpp, Ollama, and vLLM. This provides flexibility in choosing your preferred model.
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.