Dictionary Lookup MCP Server
A minimal Model Context Protocol server built with the official Python SDK. It exposes one tool, define, which looks up the definition of an English word using the free dictionaryapi.dev API.
README
Dictionary Lookup MCP Server
A minimal Model Context Protocol server
built with the official Python SDK. It exposes one tool, define, which looks
up the definition of an English word using the free
dictionaryapi.dev API.
This project was built as a learning exercise to understand how MCP servers are structured, how they communicate with clients, and how to deploy one publicly.
What it does
- Exposes a single tool:
define(word: str) -> str - Given a word, returns its part of speech and definition
- No API key or authentication required
Requirements
- Python 3.10+
- uv (recommended) or pip
Setup (local)
# 1. Clone this repo
git clone <your-repo-url>
cd my-mcp-server
# 2. Install dependencies
uv sync
Running it locally
Option A — MCP Inspector (visual testing tool, easiest for beginners):
uv run mcp dev server.py
This opens a browser-based inspector where you can call the define tool
directly and see the request/response without needing a full AI client.
Option B — Connect to Claude Desktop:
Add this to your Claude Desktop config file
(claude_desktop_config.json):
{
"mcpServers": {
"dictionary-lookup": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/my-mcp-server",
"run",
"server.py"
]
}
}
}
Restart Claude Desktop, then ask something like: "Use the dictionary tool to define 'ephemeral'."
Usage example
Input: define("ephemeral")
Output: ephemeral (adjective): lasting for a very short time.
Deployment
This server is published on Smithery: <link once deployed>
To deploy your own copy:
- Push this repo to GitHub.
- Ensure
server.pysupports thestreamable-httptransport for remote hosting. - Host it (e.g. Render/Railway) or use Smithery's publish flow.
- On Smithery, choose "Publish via URL" and point it at your hosted server's endpoint.
Why this project
Built to learn the fundamentals of MCP: how a client discovers a server's tools, how a tool call is made and answered, and how a working server gets shared publicly through a marketplace like Smithery.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。