# exec_command Execute command Agent View of the PolicyLayer registry record for `exec_command`. HTML page: https://policylayer.com/tools/eaveluo-1panel-mcp/exec-command ## Facts - Tool: `exec_command` - Server: 1Panel MCP Server (`eaveluo/1panel-mcp`) — https://policylayer.com/tools/eaveluo-1panel-mcp.md - Homepage: https://github.com/EaveLuo/1panel-mcp - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "exec_command", "arguments": {} } } ``` ## Why exec_command is rated High This tool permits execution of arbitrary shell commands on server infrastructure, which is the highest-risk Execute category operation. Misuse could compromise the entire system, modify configurations, exfiltrate data, or pivot to other systems. The blast radius is critical—an AI agent given this tool with unsafe prompting could destroy the server, install malware, or expose sensitive data. From the tool's own definition: "Tool name 'exec_command' with description 'Execute command' directly indicates arbitrary command execution capability. In the context of a server infrastructure management tool (1Panel), this allows running shell commands on the underlying system." ## Use case AI agents invoke exec_command to trigger actions in 1Panel MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 1Panel MCP Server: ```json { "version": "1", "default": "deny", "tools": { "exec_command": { "limits": [ { "counter": "exec_command_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on 1Panel MCP Server (285) - `clean_compose_log` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/clean-compose-log.md - `clean_container_log` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/clean-container-log.md - `clean_monitor_data` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/clean-monitor-data.md - `clear_recycle_bin` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/clear-recycle-bin.md - `delete_ai_agent` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-ai-agent.md - `delete_ai_agent_account` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-ai-agent-account.md - `delete_backup` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-backup.md - `delete_backup_account` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-backup-account.md - `delete_certificate` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-certificate.md - `delete_clam_config` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-clam-config.md - `delete_cronjob` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-cronjob.md - `delete_database` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-database.md - `delete_file` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-file.md - `delete_firewall_rule` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-firewall-rule.md - `delete_ftp_user` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-ftp-user.md - `delete_host` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-host.md - `delete_host_group` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-host-group.md - `delete_host_ssh_key` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-host-ssh-key.md - `delete_mcp_server` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-mcp-server.md - `delete_ollama_model` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-ollama-model.md - `delete_snapshot` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-snapshot.md - `delete_website` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-website.md - `delete_website_domain` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/delete-website-domain.md - `partition_disk` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/partition-disk.md - `prune_containers` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/prune-containers.md - `recover_snapshot` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/recover-snapshot.md - `recreate_snapshot` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/recreate-snapshot.md - `remove_compose` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/remove-compose.md - `remove_container` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/remove-container.md - `remove_image` — Destructive — https://policylayer.com/tools/eaveluo-1panel-mcp/remove-image.md - …and 255 more: https://policylayer.com/tools/eaveluo-1panel-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=eaveluo-1panel-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/eaveluo-1panel-mcp