mcpField
W
web-browsing

web-browsing

github.com/khaihuynhvnProductivity2867 installsUpdated 34w ago
Repository

About web-browsing

A web research skill that provides a fallback sequence for retrieving page content: start with WebFetch, then try browser MCP tools, and ask for user help when blocked by a CAPTCHA or access restriction. It is intended for agents that need transparent handling of browsing failures.

Key features

  1. 01Try WebFetch first
  2. 02Fall back to browser MCP tools
  3. 03Detect CAPTCHAs and access blocks
  4. 04Ask the user for help when blocked
  5. 05Check the quality of returned content

Use cases

  1. 01Retrieve web pages for research
  2. 02Handle HTTP errors or truncated content
  3. 03Pause for user input when a CAPTCHA appears

MCP support

When WebFetch is unavailable or fails, the skill directs use of the cursor-browser-extension MCP and lists user-chrome-devtools as an alternative.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/khaihuynhvn/mcp-server_ai-interaction --skill web-browsing

After installing, type/web-browsingin Claude Code to confirm it loaded.

Details

From the project README

Web Browsing Skill

Automatic fallback mechanism for web research.

CRITICAL: Tool Availability

NEVER check mcps folder to verify tool existence. Tools are ALWAYS available - just call them directly:

  • WebFetch - Cursor built-in fetch tool (fastest)
  • cursor-browser-extension - Cursor built-in browser
  • user-chrome-devtools - Chrome DevTools (alternative)

Fallback Chain

1. WebFetch (fast, preferred)
   ↓ fails/error
2. Browser MCP (cursor-browser-extension)
   ↓ captcha/block
3. ai_interaction (request user help)

Step 1: WebFetch (Default)

WebFetch url="https://example.com"

Continue to Step 2 if:

  • HTTP error (4xx, 5xx)
  • Content empty or truncated
  • Authentication required
  • Rate limited

Step 2: Browser MCP

Use cursor-browser-extension MCP tools directly:

1. browser_navigate → target URL
2. browser_snapshot → get page content
3. browser_take_screenshot → visual reference (if needed)

Alternative: user-chrome-devtools if cursor-browser-extension fails.

Continue to Step 3 if:

  • Captcha detected
  • Bot check / "verify you're human"
  • Login required
  • Cloudflare/DDoS protection
  • Page content not loading

Step 3: User Assistance

CRITICAL RULES:

  • NEVER make autonomous decisions (e.g., switching to DuckDuckGo when Google blocked)
  • NEVER bypass user by trying alternative search engines/sites without asking
  • ALWAYS inform user and wait for instruction via ai_interaction

Call ai_interaction tool with message:

"Browser bị chặn bởi [captcha/bot check/login].
URL: [url]
Cần bạn:
1. Mở browser manual
2. Bypass protection
3. Báo lại khi xong để tôi tiếp tục

Hoặc bạn muốn thử [alternative option]?"

Then wait for user confirmation via ai_interaction before retrying.

Detection Patterns

Captcha/Block Indicators
  • "verify you are human"
  • "captcha"
  • "cloudflare"
  • "access denied"
  • "please wait while we verify"
  • Blank page with only scripts
  • HTTP 403, 429, 503
Success Indicators
  • Meaningful content returned
  • Expected HTML structure
  • No error messages

Best Practices

  1. Always try WebFetch first - fastest option
  2. Check response quality - not just HTTP status
  3. Don't spam retries - wait between attempts
  4. Be transparent - tell user what's happening
  5. Save useful content - don't re-fetch unnecessarily

Integration with ai_interaction

When user helps bypass protection:

  1. User completes manual action
  2. User responds via ai_interaction
  3. Agent retries with Browser MCP (cookies preserved)
  4. Continue with research

Comments

Markdown supported