INDIVIDUAL MCP TOOL

build_llms_txt

Build an llms.txt document (per llmstxt.org): H1 name, blockquote summary, optional prose, and H2 sections of markdown links.

essentials.shnone authenticationAvailability not checked

LIVE ENDPOINT

https://essentials.sh/mcp

No auth detected

Connect to this endpoint to inspect the live schema for build_llms_txt and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.essentials-sh]
url = "https://essentials.sh/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "essentials-sh": {
      "type": "http",
      "url": "https://essentials.sh/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: essentials-sh
Remote MCP URL: https://essentials.sh/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "essentials-sh": {
      "url": "https://essentials.sh/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "essentials-sh": {
      "type": "http",
      "url": "https://essentials.sh/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "essentials-sh",
  "transport": "streamable-http",
  "url": "https://essentials.sh/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

generate_qr_svg — Generate a QR code for a URL and return it as an SVG document.
build_meta_tags — Build a complete HTML head metadata block: title, description, canonical, Open Graph, and Twitter card tags.
build_robots_txt — Build a robots.txt with AI Content Signals (search/ai-input/ai-train), optional Disallow paths, and optional hard blocks for known AI-training crawlers.
build_sitemap — Build a sitemap.xml from a site URL and a list of page paths (or absolute URLs).
scan_site — Fetch a public website and report which essentials are missing — 19 checks: title, description, mobile viewport, canonical, Open Graph tags, OG image loads, Twitter card, image alt text, favicon, custom 404 page (soft-404 detection), privacy policy, robots.txt, AI Content Signals, sitemap, llms.txt, JSON-LD, security.txt, email spoofing protection.
check_email_security — Check whether a domain is protected against email spoofing: looks up SPF, DMARC, MX, and DKIM records via DNS and returns a verdict (protected / partial / spoofable) with per-mechanism explanations and the raw records.