Fast News MCP

Fast News MCP

Search, trending, topics, and local news all in one MCP server. Article previews, deduplication, source filtering, and 40+ languages built in.

Category
访问服务器

README

Fast News MCP Server

npm version RapidAPI License

Real-time news search, trending headlines, topic categories, and local news — exposed as MCP tools so your AI agent can query news in plain language. No HTTP boilerplate required.

The server is hosted by RapidAPI and connects via mcp-remote. All you need is a RapidAPI subscription and your API key.

Demo

See the Fast News API in action: the-dispatcher-demo.vercel.app

Get an API Key

  1. Subscribe on RapidAPI (free tier available)
  2. Your API key appears on the Endpoints tab

Every request needs two headers:

Header Value
x-rapidapi-key Your API key
x-rapidapi-host fast-news-with-previews.p.rapidapi.com

Quick Start

Prerequisites: Node.js (for npx) and a free RapidAPI subscription.

Add the following to your AI agent's MCP server configuration. Replace YOUR-API-KEY with your RapidAPI key.

{
  "mcpServers": {
    "fast-news": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.rapidapi.com",
        "--header",
        "x-api-host: fast-news-with-previews.p.rapidapi.com",
        "--header",
        "x-api-key: YOUR-API-KEY"
      ]
    }
  }
}

The mcp-remote package is installed automatically by npx. You don't need to install anything manually.

See the per-agent setup instructions below for client-specific details.

<details> <summary><strong>Alternative: npm package (secondary option)</strong></summary>

Prefer the Quick Start above. Use this only if your setup specifically benefits from a single published package.

This repository is also published as the npm package @wllrdev/fast-news-mcp. It's a thin wrapper around mcp-remote that reads your key from the RAPIDAPI_KEY environment variable instead of the command line:

{
  "mcpServers": {
    "fast-news": {
      "command": "npx",
      "args": ["-y", "@wllrdev/fast-news-mcp"],
      "env": {
        "RAPIDAPI_KEY": "YOUR-API-KEY"
      }
    }
  }
}

</details>

Available Tools

Once connected, your AI agent has access to these tools:

Tool Description
search_news Search any topic with filters for language, country, and timeframe. Supports source diversity and built-in deduplication.
advanced_search Like search_news but with post-fetch controls — include/exclude specific sources, require thumbnails, and change sort order.
trending_headlines Top headlines auto-translated into 40+ languages. Optionally filter by country and timeframe.
topic_categories Browse 11 predefined categories: world, national, business, technology, entertainment, sports, science, health, politics, economy, environment. Combine two categories in one request.
local_news News about a specific city, region, or area.

For full parameter documentation, see the API reference.

Setup for Your AI Agent

Find your client below and expand it for setup steps.

<details> <summary><strong>Claude Code</strong> (<a href="https://code.claude.com/docs/en/mcp">docs</a>)</summary>

Option A — CLI command:

claude mcp add fast-news -- npx mcp-remote https://mcp.rapidapi.com --header "x-api-host: fast-news-with-previews.p.rapidapi.com" --header "x-api-key: YOUR-API-KEY"

Add --scope user to make it available globally across all projects.

Option B — Manual config:

Add the Quick Start config to your Claude Code MCP settings.

</details>

<details> <summary><strong>Claude Desktop</strong> (<a href="https://modelcontextprotocol.io/docs/develop/connect-local-servers">docs</a>)</summary>

  1. Open Claude Desktop settings
  2. Navigate to Developer > Edit Config
  3. Paste the Quick Start config into claude_desktop_config.json
  4. Restart Claude Desktop

</details>

<details> <summary><strong>Cursor</strong> (<a href="https://cursor.com/docs/mcp">docs</a>)</summary>

  1. Open Cursor Settings > MCP > New MCP Server
  2. Paste the Quick Start config
  3. Replace YOUR-API-KEY with your key
  4. Enable the server

</details>

<details> <summary><strong>VS Code Copilot</strong> (<a href="https://code.visualstudio.com/docs/copilot/customization/mcp-servers">docs</a>)</summary>

Add the following to your .vscode/mcp.json:

{
  "servers": {
    "fast-news": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.rapidapi.com",
        "--header",
        "x-api-host: fast-news-with-previews.p.rapidapi.com",
        "--header",
        "x-api-key: YOUR-API-KEY"
      ]
    }
  }
}

</details>

<details> <summary><strong>Windsurf</strong> (<a href="https://docs.windsurf.com/windsurf/cascade/mcp">docs</a>)</summary>

Add the Quick Start config to your Windsurf MCP config file (~/.codeium/windsurf/mcp_config.json).

</details>

<details> <summary><strong>Cline</strong> (<a href="https://docs.cline.bot/mcp/mcp-overview">docs</a>)</summary>

  1. Open Cline settings
  2. Go to MCP > Add New MCP Server
  3. Select Local and paste the Quick Start config

</details>

<details> <summary><strong>Continue</strong> (<a href="https://docs.continue.dev/customize/mcp-tools">docs</a>)</summary>

Add the Quick Start config to your ~/.continue/config.json under the mcpServers key.

</details>

<details> <summary><strong>OpenCode</strong> (<a href="https://opencode.ai/docs/mcp-servers">docs</a>)</summary>

Add the following to your opencode.json:

{
  "mcp": {
    "fast-news": {
      "type": "remote",
      "url": "https://mcp.rapidapi.com",
      "headers": {
        "x-api-host": "fast-news-with-previews.p.rapidapi.com",
        "x-api-key": "YOUR-API-KEY"
      }
    }
  }
}

</details>

<details> <summary><strong>Codex CLI</strong> (<a href="https://developers.openai.com/codex/mcp">docs</a>)</summary>

codex mcp add fast-news -- npx mcp-remote https://mcp.rapidapi.com --header "x-api-host: fast-news-with-previews.p.rapidapi.com" --header "x-api-key: YOUR-API-KEY"

</details>

Usage Examples

Once connected, try these prompts in your AI agent:

  • "What are the trending headlines right now?"
  • "Search for news about artificial intelligence"
  • "Find local news about Tokyo"
  • "Show me the latest technology news from the past week"
  • "Search for climate news from BBC and Reuters only, sorted by newest first"
  • "Get trending headlines in German"
  • "Find sports and business news combined"
  • "Show me health news with thumbnails only from the last 7 days"

The agent will use the MCP server to call the appropriate endpoint and return formatted results.

API Documentation

For full endpoint documentation, parameters, response formats, and code examples:

Key Features

  • Source diversity — no single domain dominates your feed (max 25% per domain)
  • Built-in deduplication — near-identical articles are collapsed automatically
  • 40+ languages — trending and topic searches auto-translate into local queries
  • Clean previews — up to 250-character excerpts with thumbnail URLs
  • Timeframe filters — last hour, 24h, 7 days, 30 days

Links

License & API Terms

The configuration and documentation in this repository are MIT licensed. The Fast News API itself is a commercial service hosted on RapidAPI — usage is subject to the RapidAPI Terms of Service and your subscription plan. The MIT license does not grant access to the API.

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选