The Hacker News MCP server (mcp-hn) gives an AI model live access to Hacker News — top, new, Ask HN and Show HN stories, full comment threads, keyword search and user profiles. It needs no API key and pulls straight from the official HN API, making it a fast way to build tech-trend, social-listening and digest agents.
Bring your own
Claude Haiku 4.5
MCP Playground runs 40+ models on the same workflow: switch anytime, or use Compare mode to run several in parallel and balance quality vs. cost.
No token required
How models use it and what it is built for.
The Hacker News MCP server wraps the Hacker News API as four MCP tools. Models can fetch lists of stories by type (top, new, ask_hn, show_hn), retrieve the comments for a specific story, search stories by query, and look up a user's profile. It runs as a stdio process and requires no credentials, since the HN API is public. Because it returns live data, an agent can summarise what the community is discussing today, track sentiment on a launch, or assemble a daily tech digest — none of which the model could do from its training data alone.
Typical tools an AI model can call. Exact names vary by version.
Copy any of these into MCP Agent Studio after connecting.
Summarise the top five Hacker News stories right now and why each is trending.
Search Hacker News for discussions about MCP and tell me the general sentiment.
Pull the comments on the top Show HN today and list the most common piece of feedback.
What has user "pg" posted about recently? Give me the highlights.
This is not a single-model product: you get the same MCP connection with 40+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.
Default pick for Hacker News
Claude Haiku 4.5
Fetching and summarising HN threads is lightweight, so Claude Haiku 4.5 keeps it fast and cheap. Use Sonnet 4.5 for deeper sentiment analysis across many threads.
Open MCP Agent Studio with the connection pre-filled. Add your token, pick any of 40+ models, and start chatting — no install required.
Open Agent StudioCommon questions about connecting, scoping and using it safely.
It is an open-source MCP server (mcp-hn) that gives AI models live access to Hacker News. It exposes tools to fetch story lists, read comment threads, search stories and look up users through the Model Context Protocol, with no API key.
Four tools: get_stories to fetch top/new/ask_hn/show_hn lists, get_story_info to read a story's comments, search_stories to search by query, and get_user_info to look up a user's profile.
No. It reads from the public Hacker News API, so it runs without any credentials — one of the quickest MCP servers to deploy and test.
Tech-trend trackers, daily digest bots, launch sentiment monitors and research agents that need current developer-community discussion. Because the data is live, the agent can report on what is being discussed today, not just at the model's training cutoff.
Open MCP Agent Studio, deploy the hosted Hacker News server from the catalog (no key needed), pick a model and ask about today's stories. You can watch each get_stories and search_stories call and its result live.
Brave Search
Give an AI agent live web and local search via the Brave Search API.
Tavily
Search, extract and crawl the web for AI research agents via Tavily.
Wikipedia
Ground AI answers in verifiable Wikipedia articles — no API key needed.
Perplexity
Get cited, web-grounded answers from an AI agent via Perplexity Sonar.
