No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by czlonkowski · MCP Server · ★ 62
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is n8n-manager-for-ai-agents safe to install? View the security audit →
n8n Manager for AI Agents [!IMPORTANT] This repository is no longer being actively developed. The n8n instance management tools have been integrated into the more comprehensive n8n-mcp project, which provides a complete solution for n8n automation with AI agents. Please use n8n-mcp for the latest features and updates. A Model Context Protocol (MCP) server that enables Claude Desktop and other AI agents to manage n8n workflow automation instances through the n8n API. 🎯 Project Overview This MCP server provides AI agents with tools to manage n8n workflows programmatically. It implements the core n8n API operations with intelligent workarounds for API limitations. ✅ What's Working Workflow Management: Create, read, update, and delete workflows Execution Monitoring: List and view execution details, delete execution records Webhook Triggers: Execute workflows via w
| Stars | 62 |
| Forks | 17 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 66.8760648070211/100 |
| Open Issues | 1 |
| Last Updated | 2025-06-26 |
| Created | 2025-06-25 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~6k |
Explore other popular mcp server tools:
n8n-manager-for-ai-agents is MCP server for Claude Desktop to manage your n8n workflows. It is categorized as a MCP Server with 62 GitHub stars.
n8n-manager-for-ai-agents is primarily written in TypeScript.
You can find installation instructions and usage details in the n8n-manager-for-ai-agents GitHub repository at github.com/czlonkowski/n8n-manager-for-ai-agents. The project has 62 stars and 17 forks, indicating an active community.
n8n-manager-for-ai-agents is released under the MIT license, making it free to use and modify according to the license terms.
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: