Labsco
AshutoshRaj97 logo

AgentReady MCP

โ˜… 1

from AshutoshRaj97

Make any website queryable by AI agents โ€” index a site and ask questions with cited answers via RAG

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅโœ“ VerifiedFreeAdvanced setup

@agentreadyweb/mcp

smithery badge

Connect any MCP client to AgentReady โ€” a hosted service that makes any website queryable by AI agents.

Claude Desktop

Add this to your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "agentready": {
      "command": "npx",
      "args": ["-y", "@agentreadyweb/mcp"]
    }
  }
}

Restart Claude Desktop. You'll have three tools available:

  • submit_site โ€” index any website so it can be queried
  • list_sites โ€” see all indexed websites
  • ask_site โ€” query any site by domain

Cursor

Add to ~/.cursor/mcp.json:

{
  "agentready": {
    "command": "npx",
    "args": ["-y", "@agentreadyweb/mcp"]
  }
}

Available tools

submit_site

submit_site(url: string)

Index a website with AgentReady. Takes ~60 seconds. Handles static sites, server-rendered pages, and JavaScript-heavy SPAs via fallback rendering. Once done, query it with ask_site.

Example: submit_site("https://docs.example.com")

list_sites

Lists all websites currently indexed by AgentReady with their titles and summaries.

ask_site

ask_site(domain: string, query: string)

Ask a question about any website and get a cited answer grounded in its content. If the site isn't indexed yet, AgentReady will crawl and index it automatically before answering.

Example: ask_site("example.com", "What does this site do?")

How indexing works

AgentReady uses a layered approach to handle any public website:

  1. llms.txt / llms-full.txt โ€” if the site publishes one, it's used as a high-quality structured content source
  2. Standard HTML crawl โ€” fetches up to 10 pages via sitemap or link crawling, extracts clean text
  3. __NEXT_DATA__ extraction โ€” for Next.js apps, parses server-side rendered data embedded in the HTML
  4. Jina Reader fallback โ€” for JS-only SPAs that return empty HTML, uses a remote rendering service to extract content

Sites behind authentication or with no public HTML content cannot be indexed.

Environment variables

VariableDefaultDescription
AGENTREADY_MCP_URLhttps://www.agentready.it.com/api/mcpOverride the MCP endpoint (for self-hosted)