Permission control plane for AI agents. MCP proxy that enforces least-privilege YAML policies on every tool call, classifies sensitive data (PII/PHI), detects dangerous skill chains, and generates compliance audit trails. Supports stdio and HTTP proxy modes.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y agentwardAgent-CoreX intelligently routes which tools from agentward-ai/agentward your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"agentward": {
"command": "npx",
"args": [
"-y",
"agentward"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add agentwardAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use agentward-ai/agentward directly without routing
npx -y agentwardNew to Agent-CoreX? View setup guide →