Home Tutorials Categories Skills About
ZH EN JA KO

Composio

Workflow Integration Browser & Automation

Install Command

npx clawhub@latest install composio

Installation Guide

1
Check Environment

Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.

2
Run Installation

Run the install command above in your terminal. ClawHub will automatically download and install Composio to the ~/.openclaw/skills/ directory.

3
Verify Installation

Run openclaw skills list to check your installed skills and confirm Composio appears in the list.

4
Configure (Optional)

Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.

Manual Installation: Copy the Skill folder to ~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Connect 250+ mainstream apps and services Pre-built automation workflow templates Unified authentication management

Detailed Description

Composio MCP Server is a pre-built workflow integration platform providing 250+ app connectors, enabling AI to easily achieve cross-platform automation operations.

Core Features

  • Multi-Platform Connections: Built-in MCP connectors for 250+ apps including GitHub, Slack, Notion, Jira, and more
  • Pre-Built Workflows: Ready-to-use templates for common automation scenarios, out of the box
  • Unified Authentication: Centralized management of OAuth and API Key authentication for all connected apps

Configuration

{
  "mcpServers": {
    "composio": {
      "command": "npx",
      "args": ["-y", "composio-mcp"],
      "env": {
        "COMPOSIO_API_KEY": "Your Composio API key"
      }
    }
  }
}

Use Cases

  • Quickly connect to multiple SaaS applications without configuring MCP servers individually
  • Create cross-app automation workflows, e.g., notify Slack after GitHub PR merge
  • Manage authentication and permissions for multiple apps through a unified interface
  • Integrate multiple external tool capabilities into AI agents