HYDRACUDA

Xtrinel-Group/HYDRACUDA

★ 3 stars Python AI/LLM Updated today

Runtime policy enforcement for AI tool calls. Define a YAML policy, drop it in front of any MCP server or LLM tool layer - every call is allowed, denied, or held for human review before it executes. The defensive counterpart to VAAST. MIT licensed, no cloud.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "hydracuda": {
      "command": "uvx",
      "args": [
        "hydracuda"
      ]
    }
  }
}

Or install with pip: pip install hydracuda

README Excerpt

<p align="center"> <img src="https://assets.xtrinel.com/hydracuda-full.svg" alt="HYDRACUDA" width="480" /> </p> Hybrid Runtime Access Control for Untrusted Delegated Actions. HYDRACUDA is a lightweight, open source policy enforcement layer for AI tool calls. Define a YAML policy file, drop HYDRACUDA in front of any MCP server or LLM tool layer, and every call is either allowed, denied, or held for review before it executes.

Tools (4)

enforceread_filereviewshadow

Topics

ai-securityllmmcpopen-sourcepolicy-enforcementpythontool-calling

HYDRACUDA

Quick Install

README Excerpt

Tools (4)

Topics

Related AI/LLM Servers