Pulumi Cloud Development MCP server for AI agents

This Python-based Datadog MCP server allows you to access your Datadog monitoring data directly through Claude, providing convenient access to monitor states and Kubernetes logs without leaving your AI interface.

Prerequisites

Python 3.11+
Datadog API and Application keys (with correct permissions)
Access to Datadog site

Installation

Via Smithery

To install Datadog for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @didlawowo/mcp-collection --client claude

Required Packages

The following Python packages are needed:

datadog-api-client
fastmcp
loguru
icecream
python-dotenv
uv

Environment Setup

Create a .env file with your Datadog credentials:

DD_API_KEY=your_api_key
DD_APP_KEY=your_app_key

Claude Desktop Setup

Install Claude Desktop:

# For macOS
brew install claude-desktop

# Or download from official website
# https://claude.ai/desktop

Configure the Datadog MCP server in your Claude config:

"Datadog-MCP-Server": {
  "command": "uv",
  "args": [
    "run",
    "--with",
    "datadog-api-client",
    "--with",
    "fastmcp",
    "--with",
    "icecream",
    "--with",
    "loguru",
    "--with",
    "python-dotenv",
    "fastmcp",
    "run",
    "/your-path/mcp-collection/datadog/main.py"
  ],
  "env": {
    "DD_API_KEY": "xxxx",
    "DD_APP_KEY": "xxx"
  }
}

The Claude config file is located at: ~/Library/Application\ Support/Claude/claude_desktop_config.json on macOS.

Available Functions

Get Monitor States

Retrieve the state of specific monitors:

get_monitor_states(
    name: str,           # Monitor name to search
    timeframe: int = 1   # Hours to look back
)

Example output:

{
    "id": "12345678",
    "name": "traefik",
    "status": "OK",
    "query": "avg(last_5m):avg:traefik.response_time{*} > 1000",
    "message": "Response time is too high",
    "type": "metric alert",
    "created": "2024-01-14T10:00:00Z",
    "modified": "2024-01-14T15:30:00Z"
}

Get Kubernetes Logs

Fetch logs from your Kubernetes clusters:

get_k8s_logs(
    cluster: str,            # Kubernetes cluster name
    timeframe: int = 5,      # Hours to look back
    namespace: str = None    # Optional namespace filter
)

Example output:

{
    "timestamp": "2024-01-14T22:00:00Z",
    "host": "worker-1",
    "service": "nginx-ingress",
    "pod_name": "nginx-ingress-controller-abc123",
    "namespace": "default",
    "container_name": "controller",
    "message": "Connection refused",
    "status": "error"
}

Troubleshooting

Common Issues

API Authentication Errors
```
Error: (403) Forbidden
```
➡️ Check your DD_API_KEY and DD_APP_KEY in .env
MCP Connection Issues
```
Error: Failed to connect to MCP server
```
➡️ Verify your claude_desktop_config.json path and content
Monitor Not Found
```
Error: No monitor found with name 'xxx'
```
➡️ Check monitor name spelling and case sensitivity

Using MCP Inspector

For debugging, you can use:

task run-mcp-inspector

This provides real-time view of server status, function call logs, error tracing, and API response monitoring.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.