OpenClaw Direct

Created By
OpenClaw Direct3 months ago
Control your fleet of OpenClaw AI assistant instances without leaving your editor. Check health, track token usage and costs, suspend or terminate instances, and manage contracts through MCP.
Overview

OpenClaw Direct MCP Server

Manage your dedicated AI assistant instances on OpenClaw Direct through natural language. Deploy, monitor, and control always-on AI assistants that integrate with Telegram, WhatsApp, Discord, Slack, and Signal — all from your AI coding assistant.

Tools (12)

Plans & Contracts

ToolDescription
list_plansList all available hosting plans with pricing and specifications
list_contractsList your subscriptions, optionally filtered by status (active, canceled, past_due)

Account Overview

ToolDescription
show_employerShow your account details and instance roster

Instance Management

ToolDescription
list_employeesList all instances with status, tier, and health info. Filter by status or include terminated instances
show_employeeShow full details for a specific instance by slug or ID
hire_employeeProvision and launch a new, pending, or previously terminated instance. Verifies an active subscription exists before starting
update_employeeRename an instance
fire_employeeTerminate an active or suspended instance

Instance Lifecycle

ToolDescription
put_employee_on_leaveSuspend an active instance without terminating it
return_employee_from_leaveResume a suspended instance back to active duty

Monitoring

ToolDescription
employee_timesheetView usage statistics for an instance over a configurable number of days (default: 30)
employee_wellness_checkRun a health check on a specific instance or all active instances at once

Setup

Requires an OpenClaw Direct account. Connect via your account's MCP access token.

Resources

  • Read our Blog for updates.

Server Config

{
  "mcpServers": {
    "openclaw": {
      "url": "https://openclaw.direct/mcp"
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
OpenClaw Direct
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago