ZpDIC MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ZpDIC MCP Serverlook up the word 'hello' in my dictionary"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: Dictionary By Api Ninjas
Installation
Clone this repository and install the dependencies:
git clone https://github.com/Eskartur/ZpDIC-MCP.git
cd zpdic-mcp
npm installEnvironment Variables
Create a .env file in the project root:
ZPDIC_API_KEY=your_zpdic_api_key_here
NGROK_AUTHTOKEN=your_ngrok_authtoken_hereGetting 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 startThe 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/mcpCopy 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/mcpAfter 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.
Related MCP Connectors
Free: turn your AI chats into spaced-repetition vocabulary. 13 tools, reads and writes.
Wiktionary MCP — multilingual dictionary via Wikimedia REST + MediaWiki Action API
- LexifyeOAuthpro.publifye
Build dictionaries & glossaries with AI: entries, senses, versions, print PDF, EPUB, web reader, RTL
Dictionary MCP — wraps Free Dictionary API (free, no auth)
Related MCP Servers
- AlicenseDqualityDmaintenanceEnables AI assistants to look up word definitions, pronunciations, and example sentences from the Cambridge Dictionary through natural language queries.114 npm7MIT
- AlicenseBqualityDmaintenanceProvides dictionary lookup functionality through the API Ninjas Dictionary API, allowing users to search for word definitions and meanings through natural language queries.1MIT
- AlicenseAqualityCmaintenanceProvides AI agents with direct access to local Yomitan dictionary databases for offline Japanese vocabulary lookups, kanji searches, and sentence tokenization. It leverages the Yomitan browser extension's API to enable rich dictionary interactions and Anki flashcard field generation.54 npm6Mozilla Public 2.0
- AlicenseNot gradedqualityCmaintenanceEnables management of Eudic dictionary wordbooks, including categories and words, directly from MCP-compatible clients like Claude Desktop.MIT