FastMCP - Model Context Protocol Server
About
# FastMCP - Model Context Protocol Server A lightweight Model Context Protocol (MCP) server implemented with [FastMCP](https://github.com/jlowin/fastmcp), a fast and Pythonic framework for building MCP servers and clients. ## Features - Create, retrieve, update, and delete model contexts - Query execution against…
Explore
- Create, retrieve, update, and delete model contexts
- Query execution against specific contexts
- Filtering by model name and tags
- In-memory storage (for development)
- FastMCP integration for easy MCP server development
- Datadog integration for metrics and monitoring
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
FastMCP - Model Context Protocol ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.7+
- FastMCP
- uv (recommended for environment management)
- Datadog account (optional, for metrics)
chmod +x install.sh
./install.sh
uv venv
uv pip install -r requirements.txt
The server integrates with Datadog for metrics and monitoring. You can configure Datadog API credentials in several ways:
Set these environment variables before starting the server:
When installing as a Claude Desktop tool, you can pass environment variables:
fastmcp install mcp_server.py --name "Model Context Server" -v DATADOG_API_KEY=your_api_key
Use the configure_datadog tool at runtime:
result = await client.call_tool("configure_datadog", {
"api_key": "your_api_key",
"app_key": "your_app_key", # Optional
"site": "datadoghq.com" # Optional
})
python mcp_server.py
fastmcp dev mcp_server.py
fastmcp install mcp_server.py --name "Model Context Server"
result = await client.call_tool("configure_datadog", {
"api_key": "your_datadog_api_key",
"app_key": "your_datadog_app_key", # Optional
"site": "datadoghq.com" # Optional
})
```
python mcp_example.py
create_context
Create a new context
get_context
Retrieve a specific context
update_context
Update an existing context
delete_context
Delete a context
list_contexts
List all contexts (with optional filtering)
query_model
Execute a query against a specific context
health_check
Server health check
configure_datadog
Configure Datadog integration at runtime
The server provides the following tools:
- create_context - Create a new context
- get_context - Retrieve a specific context
- update_context - Update an existing context
- delete_context - Delete a context
- list_contexts - List all contexts (with optional filtering)
- query_model - Execute a query against a specific context
- health_check - Server health check
- configure_datadog - Configure Datadog integration at runtime
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"fastmcp - model context protocol server": {
"datadog-mcp-server-ryuichi1208": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"datadog-mcp-server-ryuichi1208": {
"command": "uv",
"args": [
"venv"
]
}
}A lightweight Model Context Protocol (MCP) server implemented with FastMCP, a fast and Pythonic framework for building MCP servers and clients.
Features
- Create, retrieve, update, and delete model contexts
- Query execution against specific contexts
- Filtering by model name and tags
- In-memory storage (for development)
- FastMCP integration for easy MCP server development
- Datadog integration for metrics and monitoring
Requirements
- Python 3.7+
- FastMCP
- uv (recommended for environment management)
- Datadog account (optional, for metrics)
Installation
Using uv (Recommended)
The simplest way to install is using the provided scripts:
Unix/Linux/macOS
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
