Prompt capture
WebFetch tool description
17 model strings share this prompt, byte for byte.
1IMPORTANT: WebFetch WILL FAIL for authenticated or private URLs. Before using this tool, check if the URL points to an authenticated service (e.g. Google Docs, Confluence, Jira, GitHub). If so, look for a specialized MCP tool that provides authenticated access.
3- Fetches content from a specified URL and processes it using an AI model
4- Takes a URL and a prompt as input
5- Fetches the URL content, converts HTML to markdown
6- Processes the content with the prompt using a small, fast model
7- Returns the model's response about the content
8- Use this tool when you need to retrieve and analyze web content
10Usage notes:
11 - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions.
12 - The URL must be a fully-formed valid URL
13 - HTTP URLs will be automatically upgraded to HTTPS
14 - The prompt should describe what information you want to extract from the page
15 - This tool is read-only and does not modify any files
16 - Results may be summarized if the content is very large
17 - Includes a self-cleaning cache (entries expire after 15 minutes) for faster responses when repeatedly accessing the same URL
18 - When a URL redirects to a different host, the tool will inform you and provide the redirect URL in a special format. You should then make a new WebFetch request with the redirect URL to fetch the content.
19 - For GitHub URLs, prefer using the gh CLI via Bash instead (e.g., gh pr view, gh issue view, gh api).