The Data Collector
Web scraping APIs for Bluesky, Substack, and Hacker News. Pay-per-call via x402 (/bin/zsh.05 USDC). Free tier: GET /api/hn/trending (no auth needed). Built for AI agents and developers who need real-time content discovery without rate limits or account requirements.
Overview
The Data Collector-2 is an MCP server designed to facilitate targeted content search and retrieval from three distinct platforms: Hacker News, Bluesky, and Substack. By exposing dedicated search tools, it allows users to programmatically access and analyze real-time and historical data relevant to technology, social media discourse, and newsletter content.
Key Capabilities
- hn_search: Allows querying of Hacker News posts and comments, enabling extraction of trending topics, user discussions, and technology news.
- bluesky_search: Provides search access to Bluesky content, supporting retrieval of social media posts and engagement data.
- substack_search: Enables searching Substack newsletters, facilitating discovery of articles and subscription-based content.
Use Cases
- Data analysts can use hn_search to monitor emerging technology trends by querying Hacker News discussions.
- Developers integrating social media data can leverage bluesky_search to retrieve relevant posts for sentiment analysis or content aggregation.
- Content curators and marketers may use substack_search to identify popular newsletters or articles in specific niches.
- Researchers can combine data from all three tools to perform cross-platform content analysis and track information propagation.
Who This Is For
This MCP server is primarily intended for developers, data analysts, and researchers who require automated access to diverse content sources for analysis, monitoring, or integration. It suits those building data pipelines, content discovery platforms, or analytic tools that depend on aggregated data from Hacker News, Bluesky, and Substack.