Datadog Model Context Protocol (MCP)
[](https://smithery.ai/server/@didlawowo/mcp-collection)
A Python-based tool to interact with Datadog API and fetch monitoring data from your infrastructure. This MCP provides easy access to monitor states and Kubernetes logs through a simple interface.
Datadog Features
- **Monitor State Tracking**: Fetch and analyze specific monitor states
- **Kubernetes Log Analysis**: Extract and format error logs from Kubernetes clusters
Prerequisites
- Python 3.11+
- Datadog API and Application keys (with correct permissions)
- Access to Datadog site
Installation
Installing via Smithery
To install Datadog for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@didlawowo/mcp-collection):
Required packages:
Environment Setup
Create a `.env` file with your Datadog credentials:
Setup Claude Desktop Setup for MCP
- Install Claude Desktop
- Set up Datadog MCP config:
Usage
Architecture
- **FastMCP Base**: Utilizes FastMCP framework for tool management
- **Modular Design**: Separate functions for monitors and logs
- **Type Safety**: Full typing support with Python type hints
- **API Abstraction**: Wrapped Datadog API calls with error handling
I'll add a section about MCP and Claude Desktop setup:
Model Context Protocol (MCP) Introduction
What is MCP?
Model Context Protocol (MCP) is a framework allowing AI models to interact with external tools and APIs in a standardized way. It enables models like Claude to:
- Access external data
- Execute commands
- Interact with APIs
- Maintain context across conversations
some examples of MCP servers
<https://github.com/punkpeye/awesome-mcp-servers?tab=readme-ov-file>
Tutorial for setup MCP
<https://medium.com/@pedro.aquino.se/how-to-use-mcp-tools-on-claude-desktop-app-and-automate-your-daily-tasks-1c38e22bc4b0>
How it works - Available Functions
the LLM use provided function to get the data and use it
1. Get Monitor States
Example:
2. Get Kubernetes Logs
Example:
4. Verify Installation
In Claude chat desktop
check datadog connection in claude
5. Use Datadog MCP Tools
Security Considerations
- Store API keys in `.env`
- MCP runs in isolated environment
- Each tool has defined permissions
- Rate limiting is implemented
Troubleshooting
Using MCP Inspector
The MCP Inspector provides:
- Real-time view of MCP server status
- Function call logs
- Error tracing
- API response monitoring
Common issues and solutions
- **API Authentication Errors** ```bash Error: (403) Forbidden ``` Check your DD_API_KEY and DD_APP_KEY in .env
- **MCP Connection Issues** ```bash Error: Failed to connect to MCP server ``` Verify your claude_desktop_config.json path and content
- **Monitor Not Found** ```bash Error: No monitor found with name 'xxx' ``` Check monitor name spelling and case sensitivity
- **logs can be found here**
Contributing
Feel free to:
- Open issues for bugs
- Submit PRs for improvements
- Add new features
Notes
- API calls are made to Datadog EU site
- Default timeframe is 1 hour for monitor states
- Page size limits are set to handle most use cases