HackerNews-Search
A service that provides HackerNews content search, retrieval and analysis through the Model Context Protocol, suitable for AI agents and developers.
README
HackerNews数据服务 HackerNews Search
一个通过Model Context Protocol提供HackerNews内容搜索、检索和分析的服务,适用于AI代理和开发者。 A service that provides HackerNews content search, retrieval and analysis through the Model Context Protocol, suitable for AI agents and developers.## 工具列表 Tool List
本MCP服务封装下列工具,可让模型通过标准化接口调用以下功能。 本MCP服务封装下列工具,可让模型通过标准化接口调用以下功能。
| 工具 Tool | 描述 Description |
|---|---|
| search-posts | Search HackerNews for stories, comments, and other content by keyword. Supports: - Keyword search across titles, text, and authors - Tag filtering (story, comment, poll, show_hn, ask_hn, front_page, author_USERNAME) - Numeric filters for points, comments, and dates - Pagination with customizable results per page - Advanced filtering with OR logic and multiple conditions Basic Examples: - Search for AI stories: { "query": "AI", "tags": ["story"] } - Find popular posts: { "query": "Python", "numericFilters": ["points>=100"] } - Filter by author: { "query": "startup", "tags": ["author_pg"] } - Date range: { "query": "startup", "numericFilters": ["created_at_i>1640000000"] } Advanced Filtering Examples: - High engagement posts: { "query": "programming", "numericFilters": ["points>=100", "num_comments>=50"] } - OR logic for tags: { "query": "web", "tags": ["(story,poll)"] } - returns stories OR polls - Author with filters: { "query": "", "tags": ["author_pg", "story"], "numericFilters": ["points>=50"] } - Multiple conditions: { "query": "AI", "tags": ["story"], "numericFilters": ["points>=200", "num_comments>=100"] } Numeric Filter Operators: < (less than), <= (less than or equal), = (equal), >= (greater than or equal), > (greater than) Numeric Filter Fields: points, num_comments, created_at_i (Unix timestamp) Tag Syntax: - Single tag: ["story"] - only stories - Multiple tags (AND): ["story", "show_hn"] - stories that are also show_hn - OR logic: ["(story,poll)"] - stories OR polls - Author filter: ["author_USERNAME"] - posts by specific author Returns paginated results with hits, total count, and page information. |
| get-front-page | Retrieve posts currently on the HackerNews front page. Returns stories sorted by HackerNews ranking algorithm. The front page typically contains the most popular and trending stories. Supports: - Pagination to view beyond the first page - Customizable results per page (default: 30) - All posts are tagged with 'front_page' Examples: - Get first page: { } - Get with custom page size: { "hitsPerPage": 50 } - Get second page: { "page": 1 } Returns the same structure as search results with hits, pagination info, and metadata. |
| get-latest-posts | Retrieve the most recent HackerNews posts sorted by date. Returns posts in chronological order (newest first), including all types of content unless filtered. Supports: - Filter by content type using tags (story, comment, poll, show_hn, ask_hn, etc.) - Pagination to view older posts - Customizable results per page (default: 20) - Empty query to get all recent posts Examples: - Get latest stories: { "tags": ["story"] } - Get latest comments: { "tags": ["comment"] } - Get all recent activity: { } - Get with custom page size: { "hitsPerPage": 50 } Use this to monitor real-time HackerNews activity or find the newest content. |
| get-item | Retrieve detailed information about a specific HackerNews item by ID. Returns complete item details including the full nested comment tree. Use this to: - View a story with all comments - Read a specific comment with its replies - Explore discussion threads in depth - Get complete metadata for any item Features: - Full nested comment tree (all levels) - Complete item metadata (title, url, text, points, author, etc.) - Works for stories, comments, polls, and poll options - Includes creation time and item type Examples: - Get story with comments: { "itemId": "38456789" } - Get specific comment: { "itemId": "38456790" } - Get poll: { "itemId": "126809" } Note: Large comment threads (>500 comments) may take 2-3 seconds to load due to nested fetching. Returns error if item doesn't exist or has been deleted. |
| get-user | Retrieve public profile information for a HackerNews user. Returns user profile including karma, bio, and account creation date. Use this to: - Check user reputation (karma score) - Read user bio and about information - See when account was created - Verify user existence before searching their content Features: - Username (case-sensitive) - Karma score (total upvotes received) - About/bio text (may contain HTML) - Account creation date (Unix timestamp) Examples: - Get famous user: { "username": "pg" } - Check moderator: { "username": "dang" } - Verify author: { "username": "tptacek" } Username validation: - Alphanumeric characters and underscores only - Case-sensitive - Must exist on HackerNews Returns error if user doesn't exist or username format is invalid. |
检查服务 ## Inspector
工具在线测试: https://mcp.xiaobenyang.com/inspector/1777316659382275
Online Tool test https://mcp.xiaobenyang.com/inspector/1777316659382275
服务配置 MCP Server Config
如何获取 XBY-APIKEY ? How to get XBY-APIKEY ?
访问小笨羊科技网站 https://xiaobenyang.com,注册用户即可获得APIKEY Visit XiaoBenYang website https://xiaobenyang.com, register and get the APIKEY.
SSE
{
"mcpServers": {
"HackerNews数据服务": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "sse",
"url": "https://mcp.xiaobenyang.com/1777316659382275/sse"
}
}
}
STREAMABLE HTTP
{
"mcpServers": {
"HackerNews数据服务": {
"headers": {
"XBY-APIKEY": "<YOUR_XBY_APIKEY>"
},
"type": "streamable_http",
"url": "https://mcp.xiaobenyang.com/1777316659382275/mcp"
}
}
}
STDIO
{
"mcpServers": {
"HackerNews数据服务": {
"command": "npx",
"args": [
"-y",
"xiaobenyang-mcp"
],
"env": {
"XBY_APIKEY": "<YOUR_XBY_APIKEY>",
"mcpId": "1777316659382275",
},
"transport": "stdio"
}
}
}
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。