Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
## Version 0.2.0 - Initial release with full source code and documentation. - Added MCP (Model Context Protocol) orchestration utilities and API. - Implemented chat session and config synchronization functions. - Provided persistent state store via IndexedDB/localStorage. - Added examples and configuration templates for quick start.
What This Skill Does
npm package for integrating MCP (Model Context Protocol) tool servers into OpenClaw/Clawdbot agents. Provides APIs for managing MCP server lifecycles, persisting state via IndexedDB or localStorage, and merging sessions across devices.
Bundles MCP server orchestration, state persistence, and session merging into one package instead of wiring each concern separately.
When to use it
- Connecting a filesystem MCP server to read and write local files during agent tasks
- Adding a GitHub MCP server to let an agent query repos and issues
- Persisting agent state between page reloads using IndexedDB
- Syncing chat session history across multiple browser tabs or devices
- Dynamically pausing and resuming MCP servers without restarting the agent
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: set up a filesystem MCP server and read a file
- 1Call initializeMcpSystem() to start servers from mcp_config.json
- 2Call addMcpServer('fs', { command: 'npx', args: ['-y', '@modelcontextprotocol/server-filesystem', '/tmp'] }) to register the server
- 3Call getAllTools() to confirm the read_file tool is available
- 4Call executeMcpAction('fs', { method: 'tools/call', params: { name: 'read_file', arguments: { path: '/tmp/test.txt' } } }) to read the file
File contents returned from the filesystem MCP server
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.