FastMCP - MCP Server

@ryuichi1208

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

ryuichi1208

关于 FastMCP - MCP Server

暂无概览

#datadog #mcp #model-context-protocol

FastMCP - MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "datadog-mcp-server-ryuichi1208": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

FastMCP - MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is FastMCP - Model Context Protocol Server?

A lightweight MCP server built with the FastMCP framework that enables creating, retrieving, updating, and deleting model contexts, with optional Datadog integration for metrics and monitoring. It is designed for developers needing a simple in-memory context store for AI model interactions.

How to use FastMCP - Model Context Protocol Server?

Install via provided Unix/Windows scripts or manually using uv. Start the server with python mcp_server.py or uv run python mcp_server.py. Use tools such as create_context, get_context, update_context, delete_context, list_contexts, query_model, health_check, and configure_datadog. It can also be installed as a Claude Desktop tool via fastmcp install.

Key features of FastMCP - Model Context Protocol Server

Create, retrieve, update, and delete model contexts
Execute queries against specific contexts
Filter contexts by model name and tags
In-memory storage for development and testing
FastMCP integration for easy MCP server development
Datadog integration for metrics and monitoring

Use cases of FastMCP - Model Context Protocol Server

Manage model contexts for AI application development
Run queries on model contexts with filtering
Monitor server health and usage with Datadog
Prototype MCP servers locally with minimal setup
Integrate context management into Claude Desktop workflows

常见问题

What are the runtime requirements?

Python 3.7+ and FastMCP are required. `uv` is recommended for environment management. A Datadog account is optional for metrics.

How do I configure Datadog integration?

Set environment variables `DATADOG_API_KEY`, `DATADOG_APP_KEY` (optional), and `DATADOG_SITE` (optional). Alternatively, use a `.env` file or the `configure_datadog` tool at runtime.

How do I install this server as a Claude Desktop tool?

Run `fastmcp install mcp_server.py --name "Model Context Server"` optionally passing Datadog credentials with `-v DATADOG_API_KEY=your_api_key`.

What tools does the server provide?

It provides eight tools: `create_context`, `get_context`, `update_context`, `delete_context`, `list_contexts`, `query_model`, `health_check`, and `configure_datadog`.

How do I start the server?

From the activated environment, run `python mcp_server.py`. Or use `uv run python mcp_server.py` without activation. For development, use `fastmcp dev mcp_server.py`.

开发工具分类下的更多 MCP 服务器

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Termany

thinkany-ai

Agent-Native Terminal

174

Collide MCP

Lithometric Inc. | Collide Inc.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo