Model Context Protocol · no auth · free

Use awesomelist.dev from your AI agent.

This whole index — 61.4k projects across 103 awesome-lists — is a remote MCP server. Install it once and your agent can search it and recommend the right repository, with curation context attached.

61.4kprojects searchable

0tool calls, all time

0calls in the last 7 days

1distinct client apps

Install

Claude Code

One command in your terminal:

claude mcp add --transport http awesomelist https://awesomelist.dev/mcp

Claude Desktop & claude.ai

Settings → Connectors → Add custom connector, then paste:

https://awesomelist.dev/mcp

Cursor

Add to ~/.cursor/mcp.json (or project .cursor/mcp.json):

{
  "mcpServers": {
    "awesomelist": { "url": "https://awesomelist.dev/mcp" }
  }
}

VS Code (Copilot)

Add to .vscode/mcp.json:

{
  "servers": {
    "awesomelist": { "type": "http", "url": "https://awesomelist.dev/mcp" }
  }
}

Any other MCP client

Streamable HTTP transport, no auth, no API key. Point it at:

https://awesomelist.dev/mcp

Tools your agent gets

search_projects

query, limit?

Hybrid semantic + keyword search across every indexed project.

get_awesome_list

slug, limit?

Everything inside one awesome-list (metadata + curated projects).

list_categories

—

All categories with list/project counts — a map of the index.

get_trending

window?, limit?

Awesome-lists gaining the most GitHub stars over 1d / 7d / 30d.

Endpoint: https://awesomelist.dev/mcp — JSON-RPC 2.0 over Streamable HTTP (POST), stateless, unauthenticated, read-only.