ZpDIC MCP Server
Enables ChatGPT to interact with ZpDIC dictionaries, allowing word lookup, creation, deletion, and overwriting through natural language.
README
ZpDIC MCP Server
An MCP server that allows ChatGPT to use the ZpDIC API.
Prerequisites
- Node.js and npm
- A ZpDIC API key
- An ngrok account and authtoken
Installation
Clone this repository and install the dependencies:
git clone https://github.com/Eskartur/ZpDIC-MCP.git
cd zpdic-mcp
npm install
Environment Variables
Create a .env file in the project root:
ZPDIC_API_KEY=your_zpdic_api_key_here
NGROK_AUTHTOKEN=your_ngrok_authtoken_here
Getting ZPDIC_API_KEY
Log in to your ZpDIC account, open your user page, and go to the Developer tab to create or copy your API key.
Keep this key private because it allows the server to read and modify dictionary data through your ZpDIC account.
Getting NGROK_AUTHTOKEN
Create or log in to an ngrok account, then open Your Authtoken in the ngrok dashboard and copy it into NGROK_AUTHTOKEN.
The server uses this token to create a public HTTPS tunnel for your local MCP server.
Run the Server
Start the server with npm:
npm start
The server listens locally on port 6767 and prints output similar to:
Server running on http://localhost:6767
MCP available at: https://example.ngrok-free.app/mcp
Copy the full MCP available at URL, including the /mcp path.
Add to ChatGPT
In ChatGPT settings, open Apps -> Create app. Use the public ngrok URL printed by the server as the server URL:
https://example.ngrok-free.app/mcp
After saving it, ChatGPT can use the ZpDIC tools exposed by this server.
Tools
This MCP server provides the following tools:
get_word_by_number: Retrieves a single word entry by its word number.search_words: Searches word entries in a dictionary.create_word: Creates a new word entry in a dictionary.delete_word: Deletes a word entry by its word number.overwrite_word: Overwrites a word entry by its word number. Fields omitted from the new data are cleared.get_example_sentences: Retrieves example sentences for a word by its word number.
All tools share the same ZpDIC API rate limit (10 requests per minute). The MCP server automatically waits when needed and retries requests after rate limit responses.
Notes
- Keep the terminal running while using the ChatGPT app.
- The ngrok URL stays the same when you use the same ngrok account.
- Do not commit your
.envfile or share your API keys.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.