Secrets vault for Claude Code with audit logs, MCP access rules, and AES-256 encryption. Secrets are injected to local files so the AI never sees raw values. Includes session lock, device approval, and per-model access policies.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y securecode-mcpAgent-CoreX intelligently routes which tools from juanisidoro/securecode-mcp your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"securecode-mcp": {
"command": "npx",
"args": [
"-y",
"securecode-mcp"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add securecode-mcpAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use juanisidoro/securecode-mcp directly without routing
npx -y securecode-mcpNew to Agent-CoreX? View setup guide →