mcp-my-site

io.github.pournasserian/mcp-my-site

Search and fetch tools for one website, served from an index you build with the mcpmysite crawler.

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "mcp-my-site": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/pournasserian/mcp-my-site:0.4.0"
      ],
      "env": {
        "Index__Path": "<your Index__Path>",
        "AI_API_KEY": "<your AI_API_KEY>"
      }
    }
  }
}
Environment variables
  • Index__PathrequiredFolder inside the container that holds the index, the target of the mount above.
  • AI_API_KEYsecretAPI key for the embeddings provider, needed only to serve a hybrid index. Leave it unset for a keyword-only index.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Search & Web
Version
0.4.0
Registry
active
Published
10/29/2026

Remotes

  • streamable-httphttps://ai.pournasserian.com/mcp
Browse all Search & Web →

Add the badge to your site

Show visitors that mcp-my-site is listed here — it’s also the link we check for a free listing.

mcp-my-site — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-pournasserian-mcp-my-site?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="mcp-my-site — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![mcp-my-site — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-pournasserian-mcp-my-site?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.