By freema Verified
Delegate tasks to an OpenClaw AI assistant, manage conversational sessions, run long-running async operations with progress polling, and monitor gateway health. Integrates with OpenClaw for AI orchestration and claw machine management.
🦞 Model Context Protocol (MCP) server for OpenClaw AI assistant integration.
Hey! I created this MCP server because I didn't want to rely solely on messaging channels to communicate with OpenClaw. What really excites me is the ability to connect OpenClaw to the Claude web UI. Essentially, my chat can delegate tasks to my Claw bot, which then handles everything else — like spinning up Claude Code to fix issues for me.
Think of it as an AI assistant orchestrating another AI assistant. Pretty cool, right?
npx openclaw-mcp
Add to your Claude Desktop config:
{
"mcpServers": {
"openclaw": {
"command": "npx",
"args": ["openclaw-mcp"],
"env": {
"OPENCLAW_URL": "http://127.0.0.1:18789",
"OPENCLAW_GATEWAY_TOKEN": "your-gateway-token"
}
}
}
}
AUTH_ENABLED=true MCP_CLIENT_ID=openclaw MCP_CLIENT_SECRET=your-secret \
CORS_ORIGINS=https://claude.ai OPENCLAW_GATEWAY_TOKEN=your-gateway-token \
npx openclaw-mcp --transport sse --port 3000
Then in Claude.ai add a custom connector with your MCP_CLIENT_ID and MCP_CLIENT_SECRET.
See Installation Guide for details.
┌─────────────────────────────────────────────────────────────────┐
│ Your Server │
│ │
│ ┌─────────────────┐ ┌─────────────────────────┐ │
│ │ OpenClaw │ │ OpenClaw MCP │ │
│ │ Gateway │◄────►│ Bridge Server │ │
│ │ :18789 │ │ :3000 │ │
│ │ │ │ │ │
│ │ OpenAI-compat │ │ - OAuth 2.1 auth │ │
│ │ /v1/chat/... │ │ - CORS protection │ │
│ └─────────────────┘ │ - Input validation │ │
│ └──────────┬──────────────┘ │
│ │ │
└──────────────────────────────────────┼──────────────────────────┘
│ HTTPS + OAuth 2.1
▼
┌─────────────────┐
│ Claude.ai │
│ (MCP Client) │
└─────────────────┘
| Tool | Description |
|---|---|
openclaw_chat | Send messages to OpenClaw and get responses |
openclaw_status | Check OpenClaw gateway health |
| Tool | Description |
|---|---|
openclaw_chat_async | Queue a message, get task_id immediately |
openclaw_task_status | Check task progress and get results |
openclaw_task_list | List all tasks with filtering |
openclaw_task_cancel | Cancel a pending task |
⚠️ Always enable authentication in production!
# Generate secure client secret
export MCP_CLIENT_SECRET=$(openssl rand -hex 32)
# Run with auth enabled
AUTH_ENABLED=true MCP_CLIENT_ID=openclaw MCP_CLIENT_SECRET=$MCP_CLIENT_SECRET \
openclaw-mcp --transport sse
Configure CORS to restrict access:
CORS_ORIGINS=https://claude.ai,https://your-app.com
See Configuration for all security options.
MIT
Created by Tomáš Grasl
Uses power tools
Uses Bash, Write, or Edit tools
Verified owner:Tomas Grasl
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub freema/openclaw-mcp --plugin openclawSafe, scan-first macOS maintenance — inventory disk/updates/caches read-only, report reclaimable space, then clean/upgrade only what the user approves.
Connect Claude to your self-hosted vellum markdown vault: read, write, search, tags, tasks and backlinks.
Forge pixel art sprites, animations, backgrounds & thumbnails using Google Gemini. Auto prompt engineering, crop, background removal, and sprite sheet splitting.
Intelligent OpenClaw (formerly ClawdBot) installation, configuration, and management assistant. Guides users through fresh installs, 23+ channel configurations (Slack, WhatsApp, Telegram, Discord, BlueBubbles, Signal, Google Chat, Teams, Matrix, Feishu/Lark, LINE, and more), troubleshooting, security hardening, tools profiles, SecretRef secrets management, PDF tool, Docker/K8s health probes, and multi-provider model setup. If you can use Claude Code, you can use OpenClaw.
ClaudeClaw+ — governance, orchestration, persistent memory, and hardened web UI for Claude Code daemons. Sister project to moazbuilds/claudeclaw.
Cron-like daemon that runs Claude prompts on a schedule
DashClaw governance, integration, troubleshooting, and platform intelligence for Claude Code.
Unified capability management center for Skills, Agents, and Commands.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.