🌐
Fetch
Web Fetching Search & ProductivityInstall Command
npx clawhub@latest install fetch
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 Fetch to the ~/.openclaw/skills/ directory.
3
Verify Installation
Run openclaw skills list to check your installed skills and confirm Fetch 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.
Fetch webpages and convert to Markdown
Support HTML/JSON/plain text formats
Configurable request headers and proxy
Detailed Description
Fetch MCP Server is an official MCP reference implementation by Anthropic, enabling AI to fetch web content and convert it to formats suitable for large language model processing.
Core Features
- Web Fetching: Fetch web content from any URL, automatically extracting body text and removing irrelevant elements
- Format Conversion: Convert HTML content to Markdown format, also supporting raw HTML, JSON, or plain text output
- Flexible Configuration: Support for custom User-Agent, request headers, proxy settings, and content length limits
Configuration
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"],
"env": {
// Optional: set proxy
"HTTP_PROXY": "http://proxy:8080"
}
}
}
}
Use Cases
- Let AI read web documents and answer related questions
- Fetch API documentation content as coding reference
- Retrieve online data tables for analysis
- Convert web content to structured documents