MCP OpenClaw

MCP OpenClaw

An MCP server that integrates with the OpenClaw API to enable AI assistants to send messages across multiple platforms, execute system commands, and manage calendar events and emails.

Category
Visit Server

README

MCP OpenClaw

A Model Context Protocol (MCP) server that integrates with the OpenClaw API, enabling AI assistants to send messages, execute commands, manage calendar events, send emails, and track task status.

Features

  • Send Messages: Send messages to Telegram, WhatsApp, and Discord
  • Execute Commands: Run commands in the OpenClaw environment (sync or async)
  • Calendar Management: Create calendar events with attendees and reminders
  • Email: Send emails with support for CC/BCC
  • Task Status: Track the status of asynchronous commands

Installation

Global Installation

npm install -g mcp-openclaw

Local Installation

npm install mcp-openclaw

Configuration

Set the following environment variables:

export OPENCLAW_API_URL="https://api.openclaw.example.com"
export OPENCLAW_API_KEY="your-api-key-here"

Optional configuration:

export OPENCLAW_TIMEOUT="30000"        # Request timeout in milliseconds (default: 30000)
export OPENCLAW_MAX_RETRIES="3"        # Maximum retry attempts (default: 3)
export SERVER_NAME="mcp-openclaw"      # Server name (default: mcp-openclaw)
export SERVER_VERSION="1.0.0"          # Server version (default: 1.0.0)
export LOG_LEVEL="info"                # Log level: debug, info, warn, error (default: info)

Usage

With Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "openclaw": {
      "command": "node",
      "args": ["/path/to/mcp-openclaw/dist/index.js"],
      "env": {
        "OPENCLAW_API_URL": "https://api.openclaw.example.com",
        "OPENCLAW_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

1. send_message

Send a message to a supported platform.

{
  "platform": "telegram",
  "recipient": "@username",
  "message": "Hello from OpenClaw!"
}

Supported platforms: telegram, whatsapp, discord

2. execute_command

Execute a command in the OpenClaw environment.

{
  "command": "ls -la",
  "timeout": 30,
  "async": false
}

3. create_calendar_event

Create a new calendar event.

{
  "title": "Team Meeting",
  "description": "Weekly team sync",
  "startTime": "2024-01-15T10:00:00Z",
  "endTime": "2024-01-15T11:00:00Z",
  "location": "Conference Room A",
  "attendees": ["user1@example.com", "user2@example.com"],
  "reminder": 15
}

4. send_email

Send an email.

{
  "to": "recipient@example.com",
  "subject": "Hello from OpenClaw",
  "body": "This is the email content",
  "cc": "cc@example.com",
  "bcc": "bcc@example.com",
  "html": false
}

5. get_task_status

Check the status of an asynchronous command.

{
  "taskId": "task-abc123"
}

Development

Setup

git clone https://github.com/yourusername/mcp-openclaw.git
cd mcp-openclaw
npm install

Build

npm run build

Test

npm test

Lint

npm run lint
npm run lint:fix

Format

npm run format

Project Structure

mcp-openclaw/
├── src/
│   ├── index.ts              # MCP Server entry point
│   ├── types.ts              # TypeScript type definitions
│   ├── openclaw-client.ts    # OpenClaw API client
│   └── tools/
│       ├── index.ts          # Tools registry
│       ├── send-message.ts
│       ├── execute-command.ts
│       ├── create-calendar-event.ts
│       ├── send-email.ts
│       └── get-task-status.ts
├── tests/                    # Test files
├── examples/                 # Usage examples
├── docs/                     # Documentation
└── scripts/                  # Build and utility scripts

Architecture

For detailed architecture information, see docs/ARCHITECTURE.md.

API Reference

For the complete API reference, see docs/API.md.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

License

MIT License - see LICENSE for details.

Changelog

See CHANGELOG.md for version history.

Support

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured