extract_metadata

6 registry entries were observed exposing a tool named extract_metadata — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,470 of 26,658 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

1. @hauntapi/mcp-server
   trust 60/100 · BMCP serverobserved 2026-08-09 · static extraction
   MCP web extraction for permitted public pages: no-key demo plus live URL-to-JSON and Markdown output with honest blocked-page errors
2. io.github.hshintelligence/agent-scrape
   trust 60/100 · BMCP serverobserved 2026-06-14 · static extraction
   Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.
3. io.github.mysleekdesigns/crawlforge-mcp-server
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   26-tool MCP server for web scraping, crawling, deep research & autonomous extraction
4. io.github.ofershap/scraper
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Web scraping MCP — extract clean markdown, links, and metadata from any URL.
5. io.github.pipeworx-io/htmltext
   trust 60/100 · BMCP serverobserved 2026-08-12 · static extraction
   HTML → text MCP.
6. mcp-server-web-fetcher
   trust 60/100 · BMCP serverobserved 2026-08-19 · static extraction
   Turns any web page into clean Markdown, page metadata and classified links for LLMs.

All indexed toolsSearch the registry for extract_metadata