Integrations
Allows configuration of the server through .env files, enabling storage of sensitive information like API keys outside of the codebase.
Provides metrics and monitoring integration, sending data about context operations (creation, updates, deletions, access), query executions, and server events to Datadog for observability and performance tracking.
FastMCP - Model Context Protocol Server
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
Windows
Manual Installation
Datadog Configuration
The server integrates with Datadog for metrics and monitoring. You can configure Datadog API credentials in several ways:
1. Environment Variables
Set these environment variables before starting the server:
2. .env File
Create a .env
file in the project directory:
3. FastMCP CLI Installation
When installing as a Claude Desktop tool, you can pass environment variables:
4. Runtime Configuration
Use the configure_datadog
tool at runtime:
Usage
Starting the Server
Installing as a Claude Desktop Tool
Using the Tools
The server provides the following tools:
create_context
- Create a new contextget_context
- Retrieve a specific contextupdate_context
- Update an existing contextdelete_context
- Delete a contextlist_contexts
- List all contexts (with optional filtering)query_model
- Execute a query against a specific contexthealth_check
- Server health checkconfigure_datadog
- Configure Datadog integration at runtime
Example Requests
Creating a Context
Executing a Query
Configuring Datadog
Datadog Metrics
The server reports the following metrics to Datadog:
mcp.contexts.created
- Context creation eventsmcp.contexts.updated
- Context update eventsmcp.contexts.deleted
- Context deletion eventsmcp.contexts.accessed
- Context access eventsmcp.contexts.total
- Total number of contextsmcp.contexts.listed
- List contexts operation eventsmcp.queries.executed
- Query execution eventsmcp.server.startup
- Server startup eventsmcp.server.shutdown
- Server shutdown events
Development
See the included mcp_example.py
for a client implementation example:
License
MIT
Resources
This server cannot be installed
A lightweight Model Context Protocol server that enables creating, managing, and querying model contexts with integrated Datadog metrics and monitoring.
Related MCP Servers
- -securityFlicense-qualityA Model Context Protocol server built with mcp-framework that allows users to create and manage custom tools for processing data, integrating with the Claude Desktop via CLI.Last updated -484TypeScript
- -securityAlicense-qualityA Model Context Protocol server that provides file system operations, analysis, and manipulation capabilities through a standardized tool interface.Last updated -1TypeScriptMIT License
- -securityFlicense-qualityA Model Context Protocol server that provides a comprehensive interface for interacting with the ConnectWise Manage API, simplifying API discovery, execution, and management for both developers and AI assistants.Last updated -462Python
- -securityAlicense-qualityA Model Context Protocol server for data wrangling that provides standardized interfaces for data preprocessing, transformation, and analysis tasks including data aggregation and descriptive statistics.Last updated -1PythonMIT License