# OpenClaw MCP server Agent View of the PolicyLayer registry record for OpenClaw: identity, probed posture, risk grade, and all 129 tools classified. HTML page: https://policylayer.com/tools/openclaw ## Facts - Server id: `openclaw` - Install: `npx -y openclaw` - Homepage: https://www.npmjs.com/package/openclaw - Registry record: grade F, identity verified - Lifecycle: active - Rate-limited: no - Tools: 129 - Tool categories present: Destructive, Execute, Read, Write - Tags: openclaw, admin, automation - Record last modified: 2026-09-03T18:38:38.703Z ## Tools (129) | Tool | Category | Risk | Record | | --- | --- | --- | --- | | `drop` | Destructive | Critical | https://policylayer.com/tools/openclaw/drop.md | | `reset` | Destructive | Critical | https://policylayer.com/tools/openclaw/reset.md | | `uninstall` | Destructive | Critical | https://policylayer.com/tools/openclaw/uninstall.md | | `abort` | Execute | High | https://policylayer.com/tools/openclaw/abort.md | | `acp` | Execute | High | https://policylayer.com/tools/openclaw/acp.md | | `action` | Execute | High | https://policylayer.com/tools/openclaw/action.md | | `agent` | Execute | High | https://policylayer.com/tools/openclaw/agent.md | | `auth` | Execute | High | https://policylayer.com/tools/openclaw/auth.md | | `bash` | Execute | High | https://policylayer.com/tools/openclaw/bash.md | | `browser` | Execute | High | https://policylayer.com/tools/openclaw/browser.md | | `capability` | Execute | High | https://policylayer.com/tools/openclaw/capability.md | | `chat` | Execute | High | https://policylayer.com/tools/openclaw/chat.md | | `command` | Execute | High | https://policylayer.com/tools/openclaw/command.md | | `completion` | Execute | High | https://policylayer.com/tools/openclaw/completion.md | | `crestodian` | Execute | High | https://policylayer.com/tools/openclaw/crestodian.md | | `cron` | Execute | High | https://policylayer.com/tools/openclaw/cron.md | | `daemon` | Execute | High | https://policylayer.com/tools/openclaw/daemon.md | | `doctor` | Execute | High | https://policylayer.com/tools/openclaw/doctor.md | | `elevated` | Execute | High | https://policylayer.com/tools/openclaw/elevated.md | | `events_wait` | Execute | High | https://policylayer.com/tools/openclaw/events-wait.md | | `gateway` | Execute | High | https://policylayer.com/tools/openclaw/gateway.md | | `infer` | Execute | High | https://policylayer.com/tools/openclaw/infer.md | | `new` | Execute | High | https://policylayer.com/tools/openclaw/new.md | | `node` | Execute | High | https://policylayer.com/tools/openclaw/node.md | | `nodes` | Execute | High | https://policylayer.com/tools/openclaw/nodes.md | | `permissions_respond` | Execute | High | https://policylayer.com/tools/openclaw/permissions-respond.md | | `phone` | Execute | High | https://policylayer.com/tools/openclaw/phone.md | | `plugins` | Execute | High | https://policylayer.com/tools/openclaw/plugins.md | | `proxy` | Execute | High | https://policylayer.com/tools/openclaw/proxy.md | | `qa` | Execute | High | https://policylayer.com/tools/openclaw/qa.md | | `restart` | Execute | High | https://policylayer.com/tools/openclaw/restart.md | | `sandbox` | Execute | High | https://policylayer.com/tools/openclaw/sandbox.md | | `security` | Execute | High | https://policylayer.com/tools/openclaw/security.md | | `session` | Execute | High | https://policylayer.com/tools/openclaw/session.md | | `stop` | Execute | High | https://policylayer.com/tools/openclaw/stop.md | | `target` | Execute | High | https://policylayer.com/tools/openclaw/target.md | | `terminal` | Execute | High | https://policylayer.com/tools/openclaw/terminal.md | | `tui` | Execute | High | https://policylayer.com/tools/openclaw/tui.md | | `cap` | Other | Low | https://policylayer.com/tools/openclaw/cap.md | | `channel` | Other | Low | https://policylayer.com/tools/openclaw/channel.md | | `clawbot` | Other | Low | https://policylayer.com/tools/openclaw/clawbot.md | | `debounce` | Other | Low | https://policylayer.com/tools/openclaw/debounce.md | | `elev` | Other | Low | https://policylayer.com/tools/openclaw/elev.md | | `exit` | Other | Low | https://policylayer.com/tools/openclaw/exit.md | | `host` | Other | Low | https://policylayer.com/tools/openclaw/host.md | | `input` | Other | Low | https://policylayer.com/tools/openclaw/input.md | | `level` | Other | Low | https://policylayer.com/tools/openclaw/level.md | | `mode` | Other | Low | https://policylayer.com/tools/openclaw/mode.md | | `qr` | Other | Low | https://policylayer.com/tools/openclaw/qr.md | | `quit` | Other | Low | https://policylayer.com/tools/openclaw/quit.md | | `value` | Other | Low | https://policylayer.com/tools/openclaw/value.md | | `ask` | Read | Low | https://policylayer.com/tools/openclaw/ask.md | | `attachments_fetch` | Read | Low | https://policylayer.com/tools/openclaw/attachments-fetch.md | | `canvas` | Read | Low | https://policylayer.com/tools/openclaw/canvas.md | | `commands` | Read | Low | https://policylayer.com/tools/openclaw/commands.md | | `context` | Read | Low | https://policylayer.com/tools/openclaw/context.md | | `conversation_get` | Read | Low | https://policylayer.com/tools/openclaw/conversation-get.md | | `conversations_list` | Read | Low | https://policylayer.com/tools/openclaw/conversations-list.md | | `dashboard` | Read | Low | https://policylayer.com/tools/openclaw/dashboard.md | | `directory` | Read | Low | https://policylayer.com/tools/openclaw/directory.md | | `dns` | Read | Low | https://policylayer.com/tools/openclaw/dns.md | | `docs` | Read | Low | https://policylayer.com/tools/openclaw/docs.md | | `echo` | Read | Low | https://policylayer.com/tools/openclaw/echo.md | | `events_poll` | Read | Low | https://policylayer.com/tools/openclaw/events-poll.md | | `exec-policy` | Read | Low | https://policylayer.com/tools/openclaw/exec-policy.md | | `gateway-status` | Read | Low | https://policylayer.com/tools/openclaw/gateway-status.md | | `gwstatus` | Read | Low | https://policylayer.com/tools/openclaw/gwstatus.md | | `health` | Read | Low | https://policylayer.com/tools/openclaw/health.md | | `help` | Read | Low | https://policylayer.com/tools/openclaw/help.md | | `id` | Read | Low | https://policylayer.com/tools/openclaw/id.md | | `instructions` | Read | Low | https://policylayer.com/tools/openclaw/instructions.md | | `logs` | Read | Low | https://policylayer.com/tools/openclaw/logs.md | | `memory` | Read | Low | https://policylayer.com/tools/openclaw/memory.md | | `messages_read` | Read | Low | https://policylayer.com/tools/openclaw/messages-read.md | | `model` | Read | Low | https://policylayer.com/tools/openclaw/model.md | | `models` | Read | Low | https://policylayer.com/tools/openclaw/models.md | | `name` | Read | Low | https://policylayer.com/tools/openclaw/name.md | | `permissions_list_open` | Read | Low | https://policylayer.com/tools/openclaw/permissions-list-open.md | | `ping` | Read | Low | https://policylayer.com/tools/openclaw/ping.md | | `policy` | Read | Low | https://policylayer.com/tools/openclaw/policy.md | | `secrets` | Read | Low | https://policylayer.com/tools/openclaw/secrets.md | | `sessions` | Read | Low | https://policylayer.com/tools/openclaw/sessions.md | | `status` | Read | Low | https://policylayer.com/tools/openclaw/status.md | | `subagents` | Read | Low | https://policylayer.com/tools/openclaw/subagents.md | | `system` | Read | Low | https://policylayer.com/tools/openclaw/system.md | | `tasks` | Read | Low | https://policylayer.com/tools/openclaw/tasks.md | | `transcripts` | Read | Low | https://policylayer.com/tools/openclaw/transcripts.md | | `whoami` | Read | Low | https://policylayer.com/tools/openclaw/whoami.md | | `activation` | Write | Medium | https://policylayer.com/tools/openclaw/activation.md | | `active-memory` | Write | Medium | https://policylayer.com/tools/openclaw/active-memory.md | | `agents` | Write | Medium | https://policylayer.com/tools/openclaw/agents.md | | `approvals` | Write | Medium | https://policylayer.com/tools/openclaw/approvals.md | | `backup` | Write | Medium | https://policylayer.com/tools/openclaw/backup.md | | `card` | Write | Medium | https://policylayer.com/tools/openclaw/card.md | | `channels` | Write | Medium | https://policylayer.com/tools/openclaw/channels.md | | `commitments` | Write | Medium | https://policylayer.com/tools/openclaw/commitments.md | | `compact` | Write | Medium | https://policylayer.com/tools/openclaw/compact.md | | `config` | Write | Medium | https://policylayer.com/tools/openclaw/config.md | | `configure` | Write | Medium | https://policylayer.com/tools/openclaw/configure.md | | `debug` | Write | Medium | https://policylayer.com/tools/openclaw/debug.md | | `devices` | Write | Medium | https://policylayer.com/tools/openclaw/devices.md | | `dreaming` | Write | Medium | https://policylayer.com/tools/openclaw/dreaming.md | | `fast` | Write | Medium | https://policylayer.com/tools/openclaw/fast.md | | `hooks` | Write | Medium | https://policylayer.com/tools/openclaw/hooks.md | | `matrix` | Write | Medium | https://policylayer.com/tools/openclaw/matrix.md | | `mcp` | Write | Medium | https://policylayer.com/tools/openclaw/mcp.md | | `message` | Write | Medium | https://policylayer.com/tools/openclaw/message.md | | `messages_send` | Write | Medium | https://policylayer.com/tools/openclaw/messages-send.md | | `migrate` | Write | Medium | https://policylayer.com/tools/openclaw/migrate.md | | `note` | Write | Medium | https://policylayer.com/tools/openclaw/note.md | | `onboard` | Write | Medium | https://policylayer.com/tools/openclaw/onboard.md | | `pair` | Write | Medium | https://policylayer.com/tools/openclaw/pair.md | | `pairing` | Write | Medium | https://policylayer.com/tools/openclaw/pairing.md | | `path` | Write | Medium | https://policylayer.com/tools/openclaw/path.md | | `queue` | Write | Medium | https://policylayer.com/tools/openclaw/queue.md | | `reasoning` | Write | Medium | https://policylayer.com/tools/openclaw/reasoning.md | | `send` | Write | Medium | https://policylayer.com/tools/openclaw/send.md | | `settings` | Write | Medium | https://policylayer.com/tools/openclaw/settings.md | | `setup` | Write | Medium | https://policylayer.com/tools/openclaw/setup.md | | `skills` | Write | Medium | https://policylayer.com/tools/openclaw/skills.md | | `text` | Write | Medium | https://policylayer.com/tools/openclaw/text.md | | `think` | Write | Medium | https://policylayer.com/tools/openclaw/think.md | | `trace` | Write | Medium | https://policylayer.com/tools/openclaw/trace.md | | `update` | Write | Medium | https://policylayer.com/tools/openclaw/update.md | | `usage` | Write | Medium | https://policylayer.com/tools/openclaw/usage.md | | `verbose` | Write | Medium | https://policylayer.com/tools/openclaw/verbose.md | | `webhooks` | Write | Medium | https://policylayer.com/tools/openclaw/webhooks.md | | `wiki` | Write | Medium | https://policylayer.com/tools/openclaw/wiki.md | | `workboard` | Write | Medium | https://policylayer.com/tools/openclaw/workboard.md | ## Tool descriptions - `drop` — drop policy - `reset` — Reset local config/state (keeps the CLI installed) - `uninstall` — Uninstall the gateway service + local data (CLI remains) - `abort` — Abort active run - `acp` — Run and manage ACP-backed coding agents - `action` — status, start, pause, resume, complete, block, clear - `agent` — Run one agent turn via the Gateway - `auth` — Run provider auth/login flow - `bash` — Run a host command (if enabled). - `browser` — Manage OpenClaw - `capability` — Run provider capability commands (fallback alias: infer) - `chat` — Open a local terminal UI (alias for tui --local) - `command` — Shell command - `completion` — Generate shell completion script - `crestodian` — Open the interactive setup and repair assistant - `cron` — Schedule and inspect Gateway background jobs - `daemon` — Manage the Gateway service (legacy alias) - `doctor` — Diagnose and repair config, Gateway, plugin, and channel problems - `elevated` — Toggle elevated mode (on|off). - `events_wait` — Wait for the next queued OpenClaw conversation event. - `gateway` — Run, inspect, and query the OpenClaw Gateway - `infer` — Run provider-backed model, media, search, and embedding commands - `new` — Reset the session (/reset). - `node` — Run and manage the headless node host service - `nodes` — Pair nodes and run node-host commands through the Gateway - `permissions_respond` — Allow or deny one pending OpenClaw exec or plugin approval request. - `phone` — Arm/disarm high-risk phone node commands (camera/screen/writes). - `plugins` — Install, enable, disable, and inspect plugins - `proxy` — Run the OpenClaw debug proxy and inspect captured traffic - `qa` — Run QA scenarios and launch the private QA debugger UI - `restart` — Restart the gateway (if enabled). - `sandbox` — Manage sandbox containers for agent isolation - `security` — Security tools and local config audits - `session` — Switch session (or open picker) - `stop` — Stop the current run. - `target` — Run id, index, or session key - `terminal` — Open a local terminal UI (alias for tui --local) - `tui` — Open a terminal UI connected to the Gateway - `cap` — queue cap - `channel` — Voice channel to join - `clawbot` — Legacy clawbot command aliases - `debounce` — debounce duration (e.g. 500ms, 2s) - `elev` — Alias for /elevated - `exit` — Exit the TUI - `host` — sandbox, gateway, or node - `input` — Skill input - `level` — Thinking level - `mode` — compact or verbose - `qr` — Generate mobile pairing QR/setup code - `quit` — Exit the TUI - `value` — Provider, limit, or text - `ask` — off, on-miss, or always - `attachments_fetch` — List non-text attachments for a message in one OpenClaw conversation. - `canvas` — Capture or render canvas content from a paired node - `commands` — List available commands. - `context` — Explain context usage (list|detail|json). - `conversation_get` — Get one OpenClaw conversation by session key. - `conversations_list` — List OpenClaw channel-backed conversations available through session routes. - `dashboard` — Open the Control UI with your current token - `directory` — Lookup contact and group IDs (self, peers, groups) for supported chat channels - `dns` — DNS helpers for wide-area discovery (Tailscale + CoreDNS) - `docs` — Search the live OpenClaw docs - `echo` — Echo input text. - `events_poll` — Poll queued OpenClaw conversation events since a cursor. - `exec-policy` — Show or synchronize requested exec policy with host approvals - `gateway-status` — Show gateway status summary - `gwstatus` — Alias for /gateway-status - `health` — Fetch detailed health from the running Gateway - `help` — Show help and common commands. - `id` — Alias for /whoami. - `instructions` — Extra compaction instructions - `logs` — Tail Gateway logs locally or via RPC - `memory` — Search, inspect, and reindex memory files - `messages_read` — Read recent messages for one OpenClaw conversation. - `model` — Select a model (list|status|). - `models` — List, scan, and set model providers - `name` — Skill name - `permissions_list_open` — List open OpenClaw exec or plugin approval requests visible through the Gateway. - `ping` — Return OK. - `policy` — Check policy requirements and emit audit evidence - `secrets` — Audit, apply, and reload SecretRef-backed credentials - `sessions` — List stored conversation sessions - `status` — Show Gateway, channel, model, and recent-session status - `subagents` — List or manage sub-agents. - `system` — System events, heartbeat, and presence - `tasks` — Inspect durable background tasks and flows - `transcripts` — Inspect stored transcripts - `whoami` — Show sender id (alias: /id). - `activation` — Set group activation (mention|always). - `active-memory` — Enable, disable, or inspect Active Memory for this session. - `agents` — Manage isolated agents (workspaces, auth, routing) - `approvals` — Manage exec approvals (gateway or node host) - `backup` — Create and verify local backup archives for OpenClaw state - `card` — Send a rich card message (LINE). - `channels` — Add, remove, login, and inspect messaging channels - `commitments` — List and manage inferred follow-up commitments - `compact` — Compact the session history. - `config` — Non-interactive config helpers (get/set/unset/file/validate). Default: starts guided setup. - `configure` — Interactive configuration for credentials, channels, gateway, and agent defaults - `debug` — Set runtime-only overrides (owner-only). - `devices` — Device pairing + token management - `dreaming` — Enable or disable memory dreaming. - `fast` — Set fast mode on/off - `hooks` — Manage internal agent hooks - `matrix` — Manage Matrix accounts, verification, devices, and profile state - `mcp` — Manage OpenClaw MCP config and channel bridge - `message` — Send, read, and manage channel messages - `messages_send` — Send a message back through the same OpenClaw conversation route. - `migrate` — Import state from another agent system - `note` — Optional note for Codex feedback upload - `onboard` — Interactive onboarding for gateway, workspace, and skills - `pair` — Generate setup codes and approve device pairing requests. - `pairing` — Secure DM pairing (approve inbound requests) - `path` — Inspect and edit workspace files via oc:// paths - `queue` — Adjust queue mode and options. - `reasoning` — Toggle reasoning output (on|off|stream). - `send` — Set send mode (on|off|inherit). - `settings` — Open settings - `setup` — Initialize local config and an agent workspace - `skills` — List, inspect, and install agent skills - `text` — Goal objective or note - `think` — Set thinking level (off|minimal|low|medium|high|xhigh). - `trace` — Set plugin trace mode (on|off). - `update` — Update OpenClaw and inspect update channel status - `usage` — Toggle usage footer (off|tokens|full). - `verbose` — Set verbose mode (on|full|off). - `webhooks` — Webhook helpers and integrations - `wiki` — Inspect and initialize the memory wiki vault - `workboard` — List, create, inspect, and dispatch Workboard cards. ## Related servers - UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md - Delx Mcp A2a (1082 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md - Delx Protocol — Agent Recovery & Continuity (1076 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-protocol.md - Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md - MCP Framework Personal (811 tools) — https://policylayer.com/tools/inggerman-mcps.md - Delx MCP Server (740 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-server.md - Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md - Eda Agent (726 tools) — https://policylayer.com/tools/eda-agent.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=openclaw · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/openclaw