openclaw-docs-mcp
v1.0.0
Published
MCP server for searching OpenClaw documentation at docs.openclaw.ai
Maintainers
Readme
openclaw-docs-mcp
A Model Context Protocol (MCP) server for searching and retrieving documentation from OpenClaw.
Features
- 🔍 Search documentation - Full-text search across all OpenClaw docs
- 📄 Retrieve pages - Get complete content of any documentation page
- 📋 List all pages - Browse the full documentation structure
- ⚡ Fast caching - Built-in caching for improved performance
Installation
Global Installation (recommended)
npm install -g openclaw-docs-mcpLocal Installation
npm install openclaw-docs-mcpUsage
As MCP Server
Run directly:
openclaw-docs-mcpOr with npx:
npx openclaw-docs-mcpVS Code Configuration
Add to your VS Code mcp.json (~/.config/Code/User/mcp.json or %APPDATA%\Code\User\mcp.json):
{
"servers": {
"openclaw-docs": {
"type": "stdio",
"command": "npx",
"args": ["-y", "openclaw-docs-mcp"]
}
}
}For WSL users on Windows:
{
"servers": {
"openclaw-docs": {
"type": "stdio",
"command": "wsl",
"args": ["-e", "npx", "-y", "openclaw-docs-mcp"]
}
}
}Claude Desktop Configuration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"openclaw-docs": {
"command": "npx",
"args": ["-y", "openclaw-docs-mcp"]
}
}
}Available Tools
search_openclaw_docs
Search OpenClaw documentation for information about a topic.
Parameters:
query(string, required): Search query (e.g., "gateway configuration", "telegram channel")maxResults(number, optional): Maximum results to return (default: 5, max: 20)
Example:
{
"name": "search_openclaw_docs",
"arguments": {
"query": "telegram channel setup",
"maxResults": 5
}
}get_openclaw_doc_page
Get the full content of a specific documentation page.
Parameters:
path(string, required): Page path (e.g., "/gateway/configuration", "/channels/telegram")
Example:
{
"name": "get_openclaw_doc_page",
"arguments": {
"path": "/gateway/configuration"
}
}list_openclaw_doc_pages
List all available documentation pages from the sitemap.
Parameters: None
Example:
{
"name": "list_openclaw_doc_pages",
"arguments": {}
}How It Works
- Fetches the sitemap from
https://docs.openclaw.ai/sitemap.xml - Parses HTML content using Cheerio to extract text
- Performs keyword-based relevance scoring for search results
- Caches results for 5 minutes to improve performance
Development
# Clone the repository
git clone https://github.com/openclaw/openclaw-docs-mcp.git
cd openclaw-docs-mcp
# Install dependencies
npm install
# Run locally
node index.js
# Test tools/list
echo '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}' | node index.jsLicense
MIT License - see LICENSE for details.
