MCP live
Point any MCP-aware agent at https://awesome-repositories.com/api/mcp. The first tool call walks you through a one-click sign-in with Google; after that your agent can search the directory by intent, read any repository, and find its documentation. It's a read-only server — search and read, nothing to write.
Adds the server to every MCP client it detects — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Cline, Codex, Zed, Goose, Copilot CLI, and more. Append -y to skip prompts, -g for a global (user-level) install, or --agent <client> to target one.
npx add-mcp https://awesome-repositories.com/api/mcp --name awesome-repositoriesClaude Code
claude mcp add --transport http awesome-repositories https://awesome-repositories.com/api/mcpVS Code
code --add-mcp '{"name":"awesome-repositories","type":"http","url":"https://awesome-repositories.com/api/mcp"}'Cursor / Codex / Windsurf / Zed
npx add-mcp https://awesome-repositories.com/api/mcp --agent cursor # or: codex · windsurf · zed · cline · gooseClaude Desktop / any other client — paste into its MCP config
{
"mcpServers": {
"awesome-repositories": {
"type": "http",
"url": "https://awesome-repositories.com/api/mcp"
}
}
}No Authorization header — the client handles the OAuth dance for you.
Installs a skill (how to resolve intent to tag paths and search well) into every agent you have, via the well-known index at /.well-known/agent-skills/index.json. The skill teaches the agent how to drive the tools; the connection above is what actually links the server.
npx skills add https://awesome-repositories.comOAuth 2.1 — there's no token to paste. The client auto-discovers the authorization server from /.well-known/oauth-protected-resource, registers itself (Dynamic Client Registration), then opens a browser tab so you can sign in with Google. Refresh tokens keep the session alive. Every signed-in user can call every tool — this is a read-only server, so there's nothing to gate by role.
All read-only. Available to any signed-in user.
search_repositories — hybrid BM25 + AI search. AI re-rank is on by default (falls back to BM25 when the daily quota is spent); pass ai:false for raw BM25. Narrow with filter_tag_paths.search_metadata_tags — hybrid search over the unified tag tree — resolve a concept to a canonical tag path before filtering a search.get_repository — full detail for one repo by internal id or owner/repo, with tag assignments and doc counts.list_curated_searches — admin-pinned search slugs — handy discovery starting points.list_repository_docs — the documentation pages indexed for a repository (readme / doc), each with its source URL — fetch a page's body directly from that URL.