by putervision · MCP Server · ★ 69
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
| Stars | 69 |
| Forks | 1 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 59.578496563678/100 |
| Last Updated | 2026-09-15 |
| Created | 2026-07-13 |
| Platforms | mcp, node |
| Est. Tokens | ~13k |
Looking for a vision-memory-mcp alternative? If you're comparing vision-memory-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agent
Desktop app that automatically scans and blocks malicious MCP traffic in AI apps like Cursor, Claude, VS Code
MCP Fusion - The framework for AI-native MCP servers.
📜 An MCP server for conversation history search and retrieval in Claude Code
🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and
XCode CLI MCP: Convenience wrapper for Xcode CLI tools & iOS Simulator. Progressive disclosure of tool respons
Explore other popular mcp server tools:
vision-memory-mcp is Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.. It is categorized as a MCP Server with 69 GitHub stars.
vision-memory-mcp is primarily written in TypeScript. It covers topics such as ai-tool, computer-vision, developer-tools.
You can find installation instructions and usage details in the vision-memory-mcp GitHub repository at github.com/putervision/vision-memory-mcp. The project has 69 stars and 1 forks, indicating an active community.
The top alternatives to vision-memory-mcp on Agent Skills Hub include toolhive-studio, MCP-Defender, mcp-fusion. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: