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.
Exposes a single tool: define(word: str) -> str
Given a word, returns its part of speech and definition
No API key or authentication required
Related MCP server: yifanli-mcp-add-demo
Python 3.10+
uv (recommended) or pip
# 1. Clone this repo
git clone <your-repo-url>
cd my-mcp-server
# 2. Install dependencies
uv syncOption A — MCP Inspector (visual testing tool, easiest for beginners):
uv run mcp dev server.pyThis 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'."
Input: define("ephemeral")
Output: ephemeral (adjective): lasting for a very short time.
This server is published on Smithery: <link once deployed>
To deploy your own copy:
Push this repo to GitHub.
Ensure server.py supports the streamable-http transport 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.
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.
Look up the definition of an English word and return it as text.
Inputs: word (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another tool. Its purpose is immediately clear and unambiguous.
The single tool name 'define' is a clear imperative verb that matches its action. With only one tool, there are no mixed naming conventions or inconsistencies.
One tool feels thin for a server labeled as a dictionary lookup service, though it does cover the core definition lookup need. It is borderline rather than extreme.
The core lookup functionality is covered well, but a dictionary server might reasonably include related operations like synonyms, usage examples, or pronunciation. These are minor gaps rather than fatal omissions.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
A Model Context Protocol server for Wix AI tools
The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data. To get started, including information on signing up and obtaining your Ambee key, check out the Ambee documentation on https://docs.ambeedata.com
