Inoreader MCP Server
Enables intelligent RSS feed management and analysis through Inoreader integration. Supports reading articles, search, bulk operations, and AI-powered content analysis including summarization, trend analysis, and sentiment analysis.
README
Inoreader MCP Integration
An MCP (Model Context Protocol) server that integrates Inoreader with Claude Desktop, enabling intelligent RSS feed management and analysis.
Features
Feed and Article Management
- List feeds: View all your subscribed feeds
- List articles: Browse articles with filters (unread, by feed, by period)
- Read content: Access full content of specific articles
- Mark as read: Mark articles individually or in bulk
Search and Analysis
- Search articles: Search for keywords across your feeds
- Summarize articles: Generate summaries of individual articles
- Analyze multiple articles:
- Consolidated summaries
- Trend analysis
- Sentiment analysis
- Keyword extraction
- Statistics: View unread article counters
Installation
1. Clone the repository
git clone <repository-url>
cd inoreader_mcp
2. Install dependencies
pip install -r requirements.txt
3. Configure credentials
Copy the .env.example file to .env:
cp .env.example .env
Edit the .env file with your Inoreader credentials:
INOREADER_APP_ID=your_app_id
INOREADER_APP_KEY=your_app_key
INOREADER_USERNAME=your_email
INOREADER_PASSWORD=your_password
To obtain credentials:
- Visit https://www.inoreader.com/developers/
- Create a new application
- Copy the App ID and App Key
4. Configure in Claude Desktop
Add to Claude Desktop's configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"inoreader": {
"command": "python",
"args": ["/full/path/to/inoreader_mcp/main.py"],
"env": {
"INOREADER_APP_ID": "your_app_id",
"INOREADER_APP_KEY": "your_app_key",
"INOREADER_USERNAME": "your_email",
"INOREADER_PASSWORD": "your_password"
}
}
}
}
Usage
After configuration, restart Claude Desktop. Commands will be available in natural language:
Example commands
List feeds:
- "List my feeds"
- "What feeds do I follow?"
List articles:
- "Show the last 20 unread articles"
- "What unread articles do I have from TechCrunch?"
- "Show articles from the last 3 days"
Search:
- "Search articles about artificial intelligence"
- "Find Python articles from the last 7 days"
Read and mark:
- "Read article [ID]"
- "Mark all articles from feed X as read"
Analysis:
- "Summarize the top 5 AI articles this week"
- "Analyze trends in my feeds today"
- "What's the overall sentiment of economy articles?"
- "Extract keywords from unread articles"
Statistics:
- "How many unread articles do I have?"
- "Show my feed statistics"
Project Structure
inoreader_mcp/
├── main.py # Main MCP server
├── inoreader_client.py # Inoreader API client
├── tools.py # MCP tools implementation
├── config.py # Configuration and credentials
├── utils.py # Helper functions
├── requirements.txt # Python dependencies
├── .env.example # Configuration example
└── README.md # This file
Development
Testing locally
python main.py
Logs
Logs are written to console. For debugging, check Claude Desktop's console.
Limitations
- Maximum 50 articles per request
- 5-minute cache for feed list
- 10-second timeout for API requests
Troubleshooting
Authentication error:
- Verify credentials are correct
- Confirm App has necessary permissions in Inoreader
MCP doesn't appear in Claude:
- Check the full path in configuration file
- Restart Claude Desktop
- Confirm Python is in system PATH
Request timeouts:
- Inoreader API may be slow
- Try reducing the number of requested articles
Contributing
Contributions are welcome! Please:
- Fork the project
- Create a feature branch
- Commit your changes
- Push to the branch
- Open a Pull Request
License
MIT License - see LICENSE file 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。