xguard_execute — XGuard — Agent Execution Gateway MCP Tool
xguard_execute
(xguard execute) is one of 8 tools on the
XGuard — Agent Execution Gateway
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call xguard_execute from your client
- Claude Code XGuard — Agent Execution Gateway xguard_execute run in your project directory
- Claude Desktop XGuard — Agent Execution Gateway xguard_execute ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor XGuard — Agent Execution Gateway xguard_execute ~/.cursor/mcp.json
- VS Code XGuard — Agent Execution Gateway xguard_execute .vscode/mcp.json
- Zed XGuard — Agent Execution Gateway xguard_execute ~/.config/zed/settings.json
- Windsurf XGuard — Agent Execution Gateway xguard_execute ~/.codeium/windsurf/mcp_config.json
- Cline XGuard — Agent Execution Gateway xguard_execute ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI XGuard — Agent Execution Gateway xguard_execute ~/.gemini/settings.json
- Grok XGuard — Agent Execution Gateway xguard_execute .mcp.json (in your project root)
- ChatGPT XGuard — Agent Execution Gateway xguard_execute Settings → Connectors → Advanced → Developer mode
- Claude.ai XGuard — Agent Execution Gateway xguard_execute Settings → Connectors → Add custom connector
- LangChain XGuard — Agent Execution Gateway xguard_execute pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http xguard-control-plane https://api.xguardgate.com/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.