Skip to content

Web Content Extract Mcp

by varvararatta · remote · no sign-in to list tools · v1.0.0 · published by GitHub user varvararatta

Web Content Extract Mcp connects AI agents to real public APIs via MCP. Tools include

Changes · 2
CompareRegistry entry

5 tools: 2 change things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http web_content_extract_mcp https://web-content-extract-mcp.mcpize.run/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 2Claude Code: ask
  • extract_articleExtract main article content from a news/blog URL.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Extract main article content from a news/blog URL. Returns: {title, description, body, author, date}
  • health_checkServer health check.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Server health check.
Only reads 3Claude Code: allow
  • fetch_url_contentFetch and extract clean text content from a public URL.No findings

    Why it is in this group

    • The name "fetch_url_content" says "fetch": a word for reading.
    Description, as the server wrote it
    Fetch and extract clean text content from a public URL. Returns: {title, text, url, word_count}
  • get_page_linksExtract all links from a page.No findings

    Why it is in this group

    • The name "get_page_links" says "get": a word for reading.
    Description, as the server wrote it
    Extract all links from a page. Returns: {links: [href], internal_count, external_count}
  • get_page_metadataGet metadata from a page: title, description, og tags, keywords.No findings

    Why it is in this group

    • The name "get_page_metadata" says "get": a word for reading.
    Description, as the server wrote it
    Get metadata from a page: title, description, og tags, keywords. Returns: {title, description, keywords, og_title, og_image, og_type}

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http web_content_extract_mcp https://web-content-extract-mcp.mcpize.run/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__web_content_extract_mcp__fetch_url_content",
      "mcp__web_content_extract_mcp__get_page_links",
      "mcp__web_content_extract_mcp__get_page_metadata"
    ],
    "ask": [
      "mcp__web_content_extract_mcp__extract_article",
      "mcp__web_content_extract_mcp__health_check"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as web_content_extract_mcp. Review it before you use it.