| name | web-fetch |
| description | Fetches and analyzes web pages when a specific URL is provided. Use when non-developers share reference sites, API docs, or competitor pages. Complements web-research (search) with direct URL visits via WebFetch. |
Web Fetch — Visit URLs Directly
Core principle: When a URL is given, visit it directly. Don't guess what's on the page.
When to Fetch
| Phase | Fetch When |
|---|
Planning (docs/biz/) | Reference site shared, competitor analysis, API doc page |
| Development | Reading API docs, checking library pages, verifying service status |
| Communication | Non-developer asks "what does this site do?" or "make it like this" |
How to Fetch
Use the WebFetch MCP tool to retrieve page content from a URL.
- Extract URL from non-developer's message
- Fetch page content using
WebFetch
- Analyze structure, features, layout, or content
- Summarize in simple terms for non-developers
Presenting Results
- In planning docs (
docs/biz/): layout patterns, feature lists, user flows observed
- In technical docs (
docs/ai-dev/): API details, tech stack observations
- For non-developers: simple language, focus on what the site does, not how
Limitations
- Login-required pages cannot be accessed
- JavaScript-heavy SPAs may return only initial HTML
- Some sites block automated access
When blocked, ask: "Could you take a screenshot and share it instead?"
vs Web Research
- Web Research: Don't know where to look →
WebSearch
- Web Fetch: Have a specific URL →
WebFetch
