原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Ap MCP Server

作者:rbonestell版本 1.2.6i★ –i在你的电脑上运行
注册名称io.github.rbonestell/ap-mcp-server

安装

概览

作者提供的说明(英文原文)

Model Context Protocol (MCP) server for the Associated Press Media API

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他
  • 你需要填写:YOUR_API_KEY

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "ap": {
      "command": "npx",
      "args": [
        "-y",
        "ap-mcp-server"
      ],
      "env": {
        "YOUR_API_KEY": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add ap --env YOUR_API_KEY=your-value -- npx -y ap-mcp-server

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "ap": {
      "command": "npx",
      "args": [
        "-y",
        "ap-mcp-server"
      ],
      "env": {
        "YOUR_API_KEY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "ap": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ap-mcp-server"
      ],
      "env": {
        "YOUR_API_KEY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • YOUR_API_KEY 机密 必填 env
    Your API key for the service

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 rbonestell 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 18594 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 18594 个服务器的 0% 更新
  • 基础检查结果等于或优于此分类中其他 18594 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Ap MCP Server 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:YOUR_API_KEY

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.2.6)于14个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, Commonly

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

作者:formulahendry起步阶段↓ 66/周★ 44014个月前更新

在你的电脑上运行

Remote Desktop Commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

作者:desktop-commander正在增长★ 2113天前更新

在云端运行✓ desktopcommander.app

Commonly

Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.

作者:Team-Commonly正在增长↓ 4908/周今天更新

在你的电脑上运行

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Associated Press Media API MCP Server

An _unofficial_ Model Context Protocol (MCP) server that transforms the Associated Press Media API into an AI-optimized content intelligence resource. With 26 powerful tools, this MCP server enables conversational AI applications to seamlessly access, analyze, and interact with AP's comprehensive news content through natural language interfaces.

Perfect for: Conversational AI assistants, news analysis applications, content research tools, and automated journalism workflows.

[!NOTE]

For more info about the AP Media API, visit the AP developer documentation.

🔑 Key Features

🤖 Conversational AI Features
  • Natural Language Query Processing: Convert conversational queries into optimized AP API searches
  • Intelligent Prompt Templates: 17 pre-configured prompts for common workflows and use cases
  • Intelligent Content Recommendations: AI-powered content discovery and related article suggestions
  • Trend Analysis: Real-time trending topic detection and analysis
  • Smart Query Optimization: Automatic query enhancement for better search results
  • Plan Enforcement: Automatic content filtering to authorized plan items (configurable via AP_ENFORCE_PLAN)
  • AI Error Recovery: Self-healing error hints with suggested actions and retry guidance
  • Rate Limit Intelligence: Automatic rate limit detection and backoff with retry hints
  • Query Suggestions: Intelligent query refinement suggestions for broad searches
📈 Performance & Scale
  • Bulk Operations: Handle up to 2,000 search results and 50 items in single operations
  • Intelligent Caching: TTL-based caching system for improved performance
  • Auto-Pagination: Seamlessly handle large result sets with automatic pagination
  • Production-Ready: Enterprise-grade performance and reliability
📰 Complete Content Intelligence
  • 26 Comprehensive Tools: Full coverage of AP Media API functionality
  • Live Content Feeds: Real-time access to AP's breaking news and updates
  • Advanced Search: Multi-parameter search with flexible filtering and sorting
  • Content Monitoring: Create and manage automated content alerts and monitors
🛡️ Enterprise-Grade Foundation
  • Full Type Safety: Complete TypeScript implementation with OpenAPI-based types
  • Robust Error Handling: Graceful handling of API errors, rate limits, and network issues
  • Secure Configuration: Environment-based configuration with validation
  • Comprehensive Testing: High test coverage with both unit and integration tests

Quick Start

Prerequisites
  • Node.js 18+
  • An Associated Press API key (get one at api.ap.org)
Installation
Claude Code (CLI)

Add to your Claude Code MCP configuration:

{

"mcpServers": { "ap-media": { "type": "stdio", "command": "npx", "args": ["-y", "ap-mcp-server@latest"], "env": { "AP_API_KEY": "your_api_key_here" } } } }

Visual Studio Code et al.

For VS Code, Windsurf, Cursor, Void, and other VS Code-based editors:

Add the following server definition to your workspace MCP settings (.vscode/mcp.json):

{

"servers": { "ap-media": { "type": "stdio", "command": "npx", "args": ["-y", "ap-mcp-server@latest"], "env": { "AP_API_KEY": "your_api_key_here" } } } }

Generic MCP Client Configuration

Applies to Claude Desktop, ChatGPT Desktop, OpenAI Codex, etc.

For most MCP-compatible AI tools, use this standard configuration format:

{

"mcpServers": { "ap-media": { "command": "npx", "args": ["-y", "ap-mcp-server@latest"], "env": { "AP_API_KEY": "your_api_key_here" } } } }

🤖 AI & LLM Integration

The AP MCP Server is designed to be used directly by AI tools, chatbots, and LLM applications through the MCP protocol. AI assistants can access AP news content using natural language:

Natural Language AI Interactions
  • "Find recent articles about artificial intelligence in healthcare"
  • "Show me trending topics in technology this week"
  • "Get the latest breaking news about climate change"
  • "Find related articles to this story about renewable energy"

AI tools automatically convert these requests into the appropriate MCP tool calls.

Smart Content Discovery
  • Trend Detection: Automatically identify what's trending in news
  • Content Recommendations: Get AI-suggested related articles and topics
  • Query Enhancement: Transform vague queries into precise, optimized searches
  • Bulk Analysis: Process large amounts of content for pattern recognition
AI Application Types
  • News Chatbots: AI assistants with conversational access to AP news
  • Research Assistants: AI tools for journalists and researchers
  • Analysis Systems: Automated news trend and pattern analysis
  • Content Curation: AI-powered content discovery and recommendation engines

Configuration

Environment Variables
VariableRequiredDefaultDescription
AP_API_KEY✅-Your AP API key
AP_BASE_URL🚫https://api.ap.org/media/vAP API base URL
AP_TIMEOUT🚫30000Request timeout (ms)
AP_RETRIES🚫3Retry attempts for failed requests
AP_ENFORCE_PLAN🚫trueEnforce in_my_plan=true for all content requests (AI safety feature)
AP_DEBUG🚫falseEnable debug logging
AP_LOG_LEVEL🚫infoLog level (error, warn, info, debug)
AP_VERBOSE_LOGGING🚫falseEnable request/response logging
AP_CACHE_ENABLED🚫trueEnable intelligent caching system
AP_CACHE_TTL_TRENDS🚫300000Trending topics cache TTL (5 minutes)
AP_CACHE_TTL_SEARCH🚫180000Search results cache TTL (3 minutes)

🎯 MCP Prompts (17 Available)

The AP MCP Server now includes intelligent prompt templates that simplify complex operations and optimize API usage. These prompts abstract away parameter complexity and provide natural language interfaces for common workflows.

🔍 Search & Discovery Prompts
breaking-news-search

Search for the latest breaking news with optimized parameters.

  • Arguments: topic, hours_ago, location, max_results
  • Example: "Get breaking news about technology from the last 2 hours"
topic-deep-dive

Comprehensive research on a specific topic with in-depth coverage.

  • Arguments: topic, days_back, min_word_count, include_analysis, max_results
  • Example: "Deep dive into climate change coverage from the past week"
multimedia-search

Find photos, videos, graphics, and audio content.

  • Arguments: topic, media_type, days_back, high_quality_only, max_results
  • Example: "Find high-quality photos of the Olympics from the last 7 days"
regional-coverage

Get comprehensive news coverage for specific regions or locations.

  • Arguments: location, include_national, include_local, days_back, max_results
  • Example: "Get all news from California including national and local stories"
smart-search

Intelligently search with natural language queries and auto-expansion.

  • Arguments: query, search_mode, auto_expand
  • Example: "Smart search for renewable energy innovations"
📊 Analysis & Insights Prompts
trend-analysis

Analyze trending topics and patterns in news coverage.

  • Arguments: category, timeframe, location_filter, include_sentiment, max_topics
  • Example: "Analyze technology trends from the past day"
content-recommendations

Get AI-powered content recommendations based on topics or past content.

  • Arguments: based_on, subjects, content_types, location_preference, max_recommendations
  • Example: "Get recommendations based on artificial intelligence topics"
coverage-comparison

Compare news coverage across different time periods.

  • Arguments: topic, period1_days_ago, period2_days_ago, period_length_days, metrics
  • Example: "Compare election coverage between last week and this week"
quick-trending

Get a quick snapshot of what's trending right now.

  • Arguments: max_topics
  • Example: "Show me the top 10 trending topics"
🔔 Monitoring & Alert Prompts
create-news-monitor

Set up automated monitoring for specific news topics.

  • Arguments: topic, monitor_name, email, alert_frequency, description
  • Example: "Monitor breaking news about climate change every 30 minutes"
breaking-alert-setup

Quick setup for urgent breaking news alerts.

  • Arguments: topics, email, sensitivity
  • Example: "Set up high-sensitivity alerts for earthquake and tsunami news"
list-monitors

View all active content monitors and their status.

  • Arguments: include_status, include_history
  • Example: "List all my active monitors with their current status"
manage-monitor

Update or delete existing monitors.

  • Arguments: monitor_id, action, new_email, new_frequency
  • Example: "Update my climate monitor to check every 10 minutes"
📰 Workflow Prompts
daily-news-briefing

Generate a comprehensive daily news briefing.

  • Arguments: categories, location, include_breaking, include_trending, include_recommendations
  • Example: "Create a daily briefing focused on technology and business"
research-workflow

Comprehensive research workflow for investigating topics.

  • Arguments: topic, depth, time_range_days, include_multimedia, include_analysis
  • Example: "Deep research on renewable ene

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx