Overview
What is HubLens?
HubLens is an MCP server that lets AI agents query trending open-source projects and AI-generated summaries from HubLens. It wraps the HubLens Public REST API to provide structured, multi-day OSS data for grounding recommendations in Claude, Cursor, and other MCP-compatible tools.
How to use HubLens?
Install via npx -y @hublens/mcp-server and add it to your MCP client config. No API key is required. Use the tools hublens_trending, hublens_search, and hublens_article with optional parameters for filtering by category, source, or slug.
Key features of HubLens
- Query today’s trending OSS ranked by HubLens score
- Search the full HubLens archive by text, category, or source
- Fetch detailed articles with EN/ZH summaries, use cases, and tags
- Works without authentication – 60 requests per hour per IP
- All data sourced from GitHub and Hacker News, analyzed via Vertex AI
Use cases of HubLens
- Discover what AI open-source projects are trending today
- Find Rust-based vector databases or other niche OSS
- Get a quick, AI-generated summary of a specific project like langchain
FAQ from HubLens
What data does HubLens provide?
HubLens automatically detects trending OSS on GitHub and Hacker News daily, then generates English and Chinese summaries, categories, and scores via Vertex AI (Gemini). The MCP server wraps the public REST API.
Do I need an API key or any credentials?
No. The server calls public, cached endpoints and requires no authentication. It is rate-limited to 60 requests per hour per IP.
How do I install and configure HubLens?
For Claude Code: claude mcp add hublens -- npx -y @hublens/mcp-server. For other clients, add a similar entry to your MCP configuration JSON.
Where is the data stored?
The server has no local state. All data is fetched from the HubLens REST API at https://hublens.dev/api/v1/*.
What transport does the server use?
The server runs as a command-line process via npx, using the standard MCP stdio transport.
