FreshRSS MCP Server
Enables AI assistants to interact with FreshRSS feeds via the Fever API, allowing listing feeds, fetching unread items, marking items as read/unread, and managing feed subscriptions.
README
FreshRSS MCP Server
A Model Context Protocol server for interacting with FreshRSS feeds via the Fever API.
This TypeScript-based MCP server allows AI assistants to interact with your FreshRSS instance, enabling them to:
- List and browse your RSS feeds
- Fetch unread items
- Mark items as read/unread
- Get items from specific feeds
Features
Tools
list_feeds- List all feed subscriptionsget_feed_groups- Get feed groupsget_unread- Get unread itemsget_feed_items- Get items from a specific feedmark_item_read- Mark an item as readmark_item_unread- Mark an item as unreadmark_feed_read- Mark all items in a feed as readget_items- Get specific items by their IDs
Requirements
- A running FreshRSS instance with API access enabled
- API endpoint URL, username, and password for your FreshRSS instance
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Environment Variables
You need to set the following environment variables:
FRESHRSS_API_URL: URL to your FreshRSS instance (e.g., "https://rss.example.com")FRESHRSS_USERNAME: Your FreshRSS usernameFRESHRSS_PASSWORD: Your FreshRSS password
Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"freshrss": {
"command": "node",
"args": ["/path/to/freshrss-server/build/index.js"],
"env": {
"FRESHRSS_API_URL": "https://your-freshrss-instance.com",
"FRESHRSS_USERNAME": "your-username",
"FRESHRSS_PASSWORD": "your-password"
}
}
}
}
For Cline MCP integration, add to your MCP settings:
{
"mcpServers": {
"freshrss": {
"command": "node",
"args": ["/path/to/freshrss-server/build/index.js"],
"env": {
"FRESHRSS_API_URL": "https://your-freshrss-instance.com",
"FRESHRSS_USERNAME": "your-username",
"FRESHRSS_PASSWORD": "your-password"
}
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Security Note
This server requires your FreshRSS credentials. For security:
- Never commit your credentials to version control
- Always use environment variables for sensitive information
- Consider using a dedicated FreshRSS account with appropriate permissions
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! See CONTRIBUTING.md for details.
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。