Skip to content

AIblogly MCP server

Ask your AI assistant about AI models and it answers from this site: vendor prices, context windows, release dates, licences, retirement dates and current LMArena ranks for every model on the models page. Each answer includes the model’s page on aiblogly.com, which links the vendor’s own documentation. Free, read-only, no sign-up or API key.

Server address

https://www.aiblogly.com/mcp

Install

Claude Code

claude mcp add --transport http aiblogly https://www.aiblogly.com/mcp

Claude Desktop and claude.ai

Settings → Connectors → Add custom connector, then paste https://www.aiblogly.com/mcp

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "aiblogly": {
      "url": "https://www.aiblogly.com/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json:

{
  "servers": {
    "aiblogly": {
      "type": "http",
      "url": "https://www.aiblogly.com/mcp"
    }
  }
}

What you can ask it

The server offers 4 tools. Your assistant picks the right one from your question.

  • Search AI models (search_models): Find published AI models on aiblogly.com by name, vendor or category. Returns price per 1M tokens, context window, release date, licence, status and current LMArena rank, each with the model page URL to cite.
  • Get one AI model (get_model): All published facts for one model: vendor price with its conditions, context window, release date, licence, status (retired/deprecated), LMArena rank, vendor source and the date it was checked, plus a one-paragraph summary.
  • Compare two AI models (compare_models): Side-by-side facts for two models (price, context window, release date, licence, LMArena rank) and the aiblogly comparison page URL.
  • Top models by LMArena Elo (top_models): The highest-rated models in a category by current LMArena Elo (ranks older than 14 days are excluded), with links to the aiblogly rankings.

Example questions: “What does Claude Haiku 5.5 cost per million tokens?”, “Compare GPT-6 Astra and Gemini 4 Argon”, “Which video models rank highest on LMArena right now?”

Where the figures come from

  • Prices, context windows, release dates, licences and status: each vendor’s own documentation, linked from every result with the date it was checked.
  • Elo and rank: the LMArena leaderboard dataset (CC-BY-4.0), refreshed twice a day. A rank older than 14 days is left out, and Elo compares only within one category.
  • A missing figure means the vendor has not published it; nothing is estimated.

See the editorial policy for how figures are sourced.

Without MCP

The same data as one JSON file: aiblogly.com/models.json. Both are listed in llms.txt.

Source and issues

Documentation and issue tracker: github.com/spellnixinteractive/aiblogly-mcp. Report a wrong figure there with the model name and the vendor page that shows the correct value. Protocol versions 2024-11-05 to 2026-07-28, Streamable HTTP transport.