Overview

The Hacker News MCP Server allows you to retrieve specific items from Hacker News using their unique identifiers. Every story, comment, poll, and job posting on Hacker News has a unique numeric ID that you can use to fetch detailed information about that particular item. This is especially useful when you need to access a specific discussion, retrieve updated information about a story you've seen before, or dive deep into a particular comment thread.

Understanding Hacker News Item IDs

Item IDs are unique numbers assigned to every piece of content on Hacker News. You can find these IDs in the URL when browsing the site. For example, in the URL https://news.ycombinator.com/item?id=12345678, the number 12345678 is the item ID. These IDs work for stories, comments, polls, and job postings.

How to Query by ID

To retrieve a specific item, simply ask your AI assistant to fetch the Hacker News item with the ID you're interested in. For example:

• "Get Hacker News item 39847362"
• "Show me details for HN item 39821045"
• "Retrieve the Hacker News post with ID 39800123"

The server will return comprehensive information about the item, including its type (story, comment, poll, etc.), author, timestamp, text content, score, and any associated URLs.

What You'll Receive

When you query an item by ID, you'll receive structured data that varies based on the item type:

For stories, you'll get the title, URL (if it's a link post), author username, submission time, current score, and the number of comments.

For comments, you'll receive the comment text, author, timestamp, and references to parent items, allowing you to understand the conversation context.

For polls, you'll see the poll question, options, and voting information.

Practical Applications

Querying by ID is particularly valuable when you want to check for updates on a story you saw earlier, retrieve the full context of a comment someone referenced, or analyze specific discussions in detail. Since IDs are permanent and never change, you can reliably reference and retrieve the same content over time, making this feature ideal for tracking discussions, conducting research, or building collections of relevant content.