Web Fetch (Claude)
The Web Fetch (Claude) tool (anthropic_web_fetch) is a native feature from Anthropic that allows Claude to retrieve and read the content of specific web pages. This is useful when you have a specific URL whose content you want to analyze.
How It Works
Unlike web search, which collects search results, this tool retrieves the full content of a specific web page. Claude can then analyze, summarize, or answer questions about the content.
Settings
| Setting | Value |
|---|---|
| Tool key | anthropic_web_fetch |
| Default status | Disabled |
| Available for | Claude 4.0 and newer |
Disabled by Default
This tool is disabled by default. An administrator can enable it in the admin panel.
Difference from Web Search
| Web Fetch | Web Search |
|---|---|
| Retrieves one specific page | Searches multiple sources |
| Full page content | Summaries of results |
| Requires a URL | Requires a search query |
| In-depth analysis possible | Broad overview |
Usage Examples
- "Read this article and summarize it: [URL]"
- "Analyze the content of this page: [URL]"
- "What does this website say about [topic]?"
- "Get the main points from this document: [URL]"
Capabilities
- Summarize articles: Long articles into short summaries
- Extract information: Pull specific data from a page
- Compare: Compare content from multiple pages
- Translate: Understand content from foreign pages
Limitations
- Only available with Anthropic Claude models
- Some websites block automatic fetching
- Dynamic content (JavaScript) may not be fully loaded
- Pages behind login/paywall are not accessible
- Very large pages may not be fully processed
Related Tools
- Web Search (Claude) - For searching for information
- Internet Search - Universal search tool