LingQ Progress MCP
A read-only MCP server that lets ChatGPT inspect your LingQ progress without exposing your password. It exposes tools for listing languages, checking progress capabilities, and retrieving progress summaries and charts.
README
LingQ Progress MCP for ChatGPT
A tiny read-only MCP server that lets ChatGPT inspect your LingQ progress without receiving your LingQ password.
What it exposes
list_languages— active LingQ languages and the data LingQ returns for them (including known-word totals when available).inspect_progress_capabilities— asks LingQ which progress intervals/metrics are currently available.get_progress_summary— aggregate progress for a period.get_progress_chart— time-series data for a specific metric and period.
The server only performs HTTP GET requests to LingQ.
1. Requirements
- Node.js 18 or newer
- A LingQ account
- Your LingQ API key
Get your LingQ API key while logged in:
https://www.lingq.com/en/accounts/apikey/
Do not send the key to anyone. Keep it in the local .env file.
2. Configure
Open a terminal in this folder and run:
npm install
Copy .env.example to .env.
Windows PowerShell:
Copy-Item .env.example .env
notepad .env
Put your key after LINGQ_API_KEY= and save.
3. Run locally
npm start
You should see:
LingQ Progress MCP listening on http://localhost:8787/mcp
Opening http://localhost:8787/ in a browser should show a simple health message.
4. Test with MCP Inspector (recommended)
In a second terminal:
npx @modelcontextprotocol/inspector@latest
Choose Streamable HTTP and connect to:
http://localhost:8787/mcp
Call list_languages first. If it returns your LingQ languages, the key and LingQ API are working.
5. Make it reachable by ChatGPT
For a quick local test, expose port 8787 through an HTTPS tunnel such as ngrok:
ngrok http 8787
It will give you an HTTPS address. Add /mcp to the end, for example:
https://example.ngrok.app/mcp
In ChatGPT, enable Developer mode, create/add a custom plugin/MCP connection, and paste that HTTPS /mcp URL.
Then you can ask things like:
- "Como tá meu russo no LingQ essa semana?"
- "Quantas palavras conhecidas eu tenho em russo e japonês?"
- "Compara meu progresso dos últimos 7 e 30 dias."
- "Quanto tempo eu ouvi neste mês?"
- "Mostra quais dias eu mais li esta semana."
Security notes
- The LingQ API key stays on the computer/server running this project.
- The MCP responses never intentionally include the API key.
- All LingQ calls in this project are
GETrequests only. - Do not commit
.envto Git; it is already included in.gitignore.
LingQ API caveat
LingQ's public API documentation is incomplete/outdated. The project therefore includes inspect_progress_capabilities, which asks the live LingQ progress endpoint what it currently supports instead of assuming every metric name forever.
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.