Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y mcp-dandanAgent-CoreX intelligently routes which tools from 82ch/MCP-Dandan your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"mcp-dandan": {
"command": "npx",
"args": [
"-y",
"mcp-dandan"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add mcp-dandanAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use 82ch/MCP-Dandan directly without routing
npx -y mcp-dandanNew to Agent-CoreX? View setup guide →