Sonarr & Radarr MCP Server
Enables interaction with Sonarr and Radarr APIs to query media libraries, check recent additions, view upcoming releases, manage download queues, and perform searches for TV shows and movies through natural language.
README
Sonarr & Radarr MCP Server
A secure, production-ready Model Context Protocol (MCP) server for interacting with Sonarr and Radarr APIs. This server enables Claude to query your media library, check recent additions, view upcoming releases, and perform basic management tasks.
Features
Sonarr
- Get recently added TV series
- View upcoming episode calendar
- Search series in your library
- Check system status and disk space
- View download queue
- Refresh series metadata
- Trigger episode searches
Radarr
- Get recently added movies
- View upcoming movie releases
- Search movies in your library
- Check system status and disk space
- View download queue
- Refresh movie metadata
- Trigger movie searches
Security Features
This MCP server is built with security as a priority:
- Non-root container execution: Runs as user ID 1000 (non-root)
- Read-only root filesystem: Container filesystem is immutable
- No privilege escalation: Container cannot gain additional privileges
- Dropped capabilities: All Linux capabilities dropped
- Secrets management: API keys stored in Kubernetes secrets
- Network policies: Restricts network access to only necessary services
- Resource limits: CPU and memory limits prevent resource exhaustion
- Secure defaults: Follows security best practices from the ground up
Prerequisites
- Docker (for containerization)
- Kubernetes cluster (for deployment)
- Sonarr instance with API access
- Radarr instance with API access
- Python 3.12+ (for local development)
Quick Start
1. Clone and Configure
git clone <your-repo-url>
cd mcp-servarr
2. Set Up Environment Variables
Copy the example environment file:
cp .env.example .env
Edit .env with your actual values:
# Sonarr Configuration
SONARR_URL=http://your-sonarr-host:8989
SONARR_API_KEY=your-sonarr-api-key
# Radarr Configuration
RADARR_URL=http://your-radarr-host:7878
RADARR_API_KEY=your-radarr-api-key
Finding your API keys:
- Sonarr: Settings → General → Security → API Key
- Radarr: Settings → General → Security → API Key
3. Build the Docker Image
docker build -t mcp-servarr:latest .
4. Test Locally with Docker Compose
docker-compose up
Kubernetes Deployment
1. Update Secrets
Edit k8s/deployment.yaml and replace the placeholder API keys in the Secret:
stringData:
SONARR_URL: "http://sonarr.media.svc.cluster.local:8989"
SONARR_API_KEY: "your-actual-sonarr-api-key"
RADARR_URL: "http://radarr.media.svc.cluster.local:7878"
RADARR_API_KEY: "your-actual-radarr-api-key"
Security Note: For production, use kubectl create secret instead of storing secrets in YAML:
kubectl create secret generic mcp-servarr-secrets \
--namespace=mcp-servarr \
--from-literal=SONARR_URL='http://sonarr:8989' \
--from-literal=SONARR_API_KEY='your-key' \
--from-literal=RADARR_URL='http://radarr:7878' \
--from-literal=RADARR_API_KEY='your-key'
2. Deploy to Kubernetes
kubectl apply -f k8s/deployment.yaml
3. Verify Deployment
kubectl get pods -n mcp-servarr
kubectl logs -n mcp-servarr deployment/mcp-servarr
Connecting to Claude
To use this MCP server with Claude Desktop, add it to your MCP settings:
Using Docker
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"mcp-servarr": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--env-file", "/path/to/your/.env",
"mcp-servarr:latest"
]
}
}
}
Using Python (Development)
{
"mcpServers": {
"mcp-servarr": {
"command": "python",
"args": [
"/path/to/mcp-servarr/src/server.py"
],
"env": {
"SONARR_URL": "http://localhost:8989",
"SONARR_API_KEY": "your-key",
"RADARR_URL": "http://localhost:7878",
"RADARR_API_KEY": "your-key"
}
}
}
}
Usage Examples
Once connected to Claude, you can ask questions like:
- "What TV shows were added to Sonarr this week?"
- "What movies are coming out in the next 30 days?"
- "Search for Breaking Bad in my library"
- "What's currently downloading in Radarr?"
- "Show me Sonarr's system status"
- "Refresh the metadata for series ID 123"
API Reference
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
SONARR_URL |
No* | - | Sonarr base URL (e.g., http://sonarr:8989) |
SONARR_API_KEY |
No* | - | Sonarr API key |
RADARR_URL |
No* | - | Radarr base URL (e.g., http://radarr:7878) |
RADARR_API_KEY |
No* | - | Radarr API key |
REQUEST_TIMEOUT |
No | 30 | HTTP request timeout in seconds |
*At least one service (Sonarr or Radarr) must be configured
Available Tools
Sonarr Tools
sonarr_get_recent_series- Get recently added seriessonarr_get_calendar- Get upcoming episodessonarr_search_series- Search for seriessonarr_get_system_status- Get system statussonarr_get_queue- Get download queuesonarr_refresh_series- Refresh series metadatasonarr_search_episodes- Search for missing episodes
Radarr Tools
radarr_get_recent_movies- Get recently added moviesradarr_get_calendar- Get upcoming releasesradarr_search_movies- Search for moviesradarr_get_system_status- Get system statusradarr_get_queue- Get download queueradarr_refresh_movie- Refresh movie metadataradarr_search_movie- Search for a movie
Development
Local Development Setup
- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Run the server:
export SONARR_URL=http://localhost:8989
export SONARR_API_KEY=your-key
export RADARR_URL=http://localhost:7878
export RADARR_API_KEY=your-key
python src/server.py
Testing
Test the server using the MCP Inspector:
npx @modelcontextprotocol/inspector python src/server.py
Troubleshooting
Connection Issues
Problem: Cannot connect to Sonarr/Radarr
Solutions:
- Verify URLs are correct (include http:// or https://)
- Check API keys are valid
- Ensure Sonarr/Radarr are accessible from the container
- Check network policies in Kubernetes
Permission Errors
Problem: Container fails with permission errors
Solutions:
- Verify the container runs as non-root (UID 1000)
- Check volume mount permissions
- Ensure read-only filesystem is properly configured
API Rate Limiting
Problem: Getting rate limited by APIs
Solutions:
- Increase
REQUEST_TIMEOUTif requests are timing out - Reduce frequency of queries
- Check Sonarr/Radarr logs for issues
Security Considerations
Production Deployment Checklist
- [ ] Use Kubernetes Secrets for API keys (not ConfigMaps)
- [ ] Enable Pod Security Standards (restricted profile)
- [ ] Configure network policies to limit egress traffic
- [ ] Set appropriate resource limits
- [ ] Enable audit logging
- [ ] Use private container registry
- [ ] Scan images for vulnerabilities
- [ ] Rotate API keys regularly
- [ ] Use TLS for Sonarr/Radarr connections
- [ ] Implement monitoring and alerting
API Key Security
Never commit API keys to version control!
For production:
- Use Kubernetes secrets
- Consider using a secrets manager (Vault, Sealed Secrets, etc.)
- Rotate keys regularly
- Use separate API keys for different environments
- Enable API key authentication logging in Sonarr/Radarr
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Guidelines
- Follow existing code style
- Add tests for new features
- Update documentation
- Ensure security best practices
- Test in both Docker and Kubernetes
License
MIT License - See LICENSE file for details
Support
For issues, questions, or contributions, please open an issue on GitHub.
Acknowledgments
- Built with the Model Context Protocol SDK
- Uses Sonarr API
- Uses Radarr API
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。