ai-resources

ai-resources-mcp

An MCP server that gives any AI agent the AI Resources news layer: daily briefings on AI models, companies, funding rounds, tools and research, searchable and citable. It reads the public API of blogs.drix10.com; no key needed.

Tool	What it does
search_briefings(query, category?, limit?, since?)	Keyword search, newest first. All words must match. since is YYYY-MM-DD.
latest(category?, limit?)	The newest briefings, overall or for one category.
get_briefing(id)	Full Markdown of one briefing (URL or slug), with every source link.
list_categories()	Every category slug with its briefing count.

Every result ends with its source link and Data: github.com/Drix10/ai-resources (CC BY 4.0), so answers stay citable.

Install

· in the official MCP Registry as io.github.Drix10/ai-resources. Node.js 18+, no key, no account.

Claude Code

claude mcp add ai-resources -- npx -y ai-resources-mcp

Claude Desktop (claude_desktop_config.json), Cursor (~/.cursor/mcp.json or .cursor/mcp.json) and Windsurf (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "ai-resources": { "command": "npx", "args": ["-y", "ai-resources-mcp"] }
  }
}

VS Code (.vscode/mcp.json):

{
  "servers": {
    "ai-resources": { "type": "stdio", "command": "npx", "args": ["-y", "ai-resources-mcp"] }
  }
}

or from a terminal: code --add-mcp "{\"name\":\"ai-resources\",\"command\":\"npx\",\"args\":[\"-y\",\"ai-resources-mcp\"]}"

On Windows, if a client cannot start npx, use "command": "cmd", "args": ["/c", "npx", "-y", "ai-resources-mcp"].

Settings

AI_RESOURCES_API_URL: base URL of the API (default https://blogs.drix10.com). Node 18 or later.

The API underneath

Usable without MCP, from any HTTP client (CORS open, JSON):

• GET /api/articles?q=&category=&since=&limit=&page=: { items: [{ title, url, slug, category, categorySlug, date, description, headlines, sources: [{ title, url }] }], total, page, limit, totalPages, license }
• GET /api/articles?slug=<slug or URL>: one item, plus content (full Markdown)
• GET /api/categories: { items: [{ name, slug, count, url, llms }] }
• GET /llms.txt and GET /llms/<category-slug>.txt: the latest 50 briefings of a category in llms.txt form

Develop

git clone https://github.com/Drix10/ai-resources
cd ai-resources/mcp
npm ci
npm test          # node:test against a stubbed fetch

Issues labelled mcp are open for contributors; see CONTRIBUTING.md.

Code: MIT. Data: Drix10/ai-resources, CC BY 4.0.