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 hjlarry · MCP Server · ★ 66
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dify-plugin-mcp_server safe to install? View the security audit →
MCP Server Author: hjlarry Version: 0.0.4 Type: extension Repo: https://github.com/hjlarry/dify-plugin-mcpserver Feature Request: issues A Dify endpoint plugin that change a dify app to a mcp server. To keep your data secure, use this plugin exclusively within your private network. Get Started create a simple workflow app in dify. add a endpoint and select this app. The app's input schema must define its input parameters. For a chat dify app, ensure to include a field in the input schema, formatted as follows: copy the endpoint url to your mcp client, like Option 1: Use the newest Streamable HTTP protocol (Recommended) Option 2: Use the legacy SSE protocol enjoy it! To keep your data secure, you can add a on the endpoint setting. For example, if your Auth Bearer T
| Stars | 66 |
| Forks | 20 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 47.926898798655/100 |
| Open Issues | 10 |
| Last Updated | 2025-06-19 |
| Created | 2025-03-18 |
| Platforms | mcp, python |
| Est. Tokens | ~253k |
Explore other popular mcp server tools:
dify-plugin-mcp_server is an open-source mcp server by hjlarry with 66 GitHub stars.
dify-plugin-mcp_server is primarily written in Python.
You can find installation instructions and usage details in the dify-plugin-mcp_server GitHub repository at github.com/hjlarry/dify-plugin-mcp_server. The project has 66 stars and 20 forks, indicating an active community.
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: