Fetches content from a specified URL and processes it for analysis.
- Takes a URL and optional `timeout_ms` as input
- HTML content is automatically converted to markdown for easier reading
- JSON content is automatically prettified
- Other content types are returned as-is
- Use this tool when you need to retrieve and analyze web content
### Parameters
- `url`: The URL to fetch content from (required)
- Must be a fully-formed valid URL
- HTTP URLs will be automatically upgraded to HTTPS
- `timeout_ms`: Optional timeout in milliseconds (default varies by implementation)
### Usage Notes
- IMPORTANT: If another tool is present that offers better web fetching capabilities, is more targeted to the task, or has fewer restrictions, prefer using that tool instead of this one.
- The URL must be a fully-formed valid URL (e.g., "https://example.com/page")
- HTTP URLs will be automatically upgraded to HTTPS for security
- Redirects are followed automatically
- This tool is read-only and does not modify any files
- Results may be summarized if the content is very large
### When to Use This Tool
- Fetching documentation from the web
- Reading API references or library documentation
- Retrieving content from URLs provided by the user
- Checking website content for analysis
### When NOT to Use This Tool
- For local file operations - use Read tool instead
- For searching the web - this only fetches specific URLs
- When another MCP tool offers better web capabilities
### Examples
Fetching a documentation page:
```
url: "https://docs.rust-lang.org/book/ch01-00-getting-started.html"
```
Fetching with custom timeout:
```
url: "https://api.example.com/large-response"
timeout_ms: 30000
```
### Best Practices
1. Provide complete URLs including the protocol (https://)
2. Use this tool for specific URLs, not for web searching
3. If content is very large, results may be summarized - ask for specific sections if needed
4. Consider timeout settings for slow-loading pages