Skip to content
MCP server

Langrit

Language-learning memory for AI tutors: due reviews, mistakes and level

Pricing
Freemium
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
2 days ago

About Langrit

Langrit is a freemium MCP server for language learning. It runs as a hosted remote server, so there is nothing to install locally.

Langrit lets Claude, ChatGPT, Cursor and other MCP clients share one learning record. Each correction your tutor makes becomes a flashcard that returns later in a new sentence, and a spaced-repetition queue decides what to quiz next. Saying "today's session" starts a review of what is due before new teaching.

The pitch against built-in chat memory is that Langrit keeps mistakes word for word, schedules them, checks you fixed them and shows recurring patterns week by week. Mistakes made in chat appear on the Mistakes page of the Langrit app, in tomorrow's reviews and in your level, and everything can be exported as JSON, CSV or Anki.

Builders get a standard MCP server with OAuth 2.1, a REST API and personal tokens; the example call uses a whats_due tool.

Install

Run in a terminal

claude mcp add --transport http langrit https://langrit.com/mcp

Add to Settings → Connectors → Add custom connector

https://langrit.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "langrit": {
      "url": "https://langrit.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "langrit": {
      "type": "http",
      "url": "https://langrit.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "langrit": {
      "serverUrl": "https://langrit.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "langrit": {
      "type": "http",
      "url": "https://langrit.com/mcp"
    }
  }
}

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

whats_due
Fetches the cards due for review (shown in the builder example call)

What it does

Mistake memory
Saves each correction as a card that returns in a new sentence.
Due-review queue
The same spaced-repetition queue as the app, quizzed in the right question type.
Error patterns
Shows what you keep getting wrong and picks the day's focus.
Shared across apps
One record used by Claude, ChatGPT, Claude Code, Cursor, VS Code or your own agent.
Export
Take everything out as JSON, CSV or Anki.
Builder access
OAuth 2.1 MCP server, REST API and personal tokens.

Good for

  • Start a daily review session inside Claude or ChatGPT
  • Keep one mistake history across several AI apps
  • See weekly top error patterns
  • Build a custom tutor bot on the REST API
  • Export flashcards to Anki

Pricing

Freemium

Memory plan free; Premium 6.99 EUR/month with 14-day trial

Prices change. Check langrit.com before you buy.

Langrit FAQ

Is the memory plan free?

Yes. The site says the Memory plan is free forever with no card; Premium adds the Langrit app.

What does Premium cost?

6.99 euros a month, with a 14-day trial and no card needed.

What happens if I stop paying?

Your account moves to the free Memory plan and nothing is lost.

Can I get my data out?

Yes, as JSON, CSV or Anki.

How do I connect?

Add langrit.com/mcp as a connector in your AI app and sign in once.

Is Langrit free?

Langrit has a free plan, with paid plans for more usage or features.

How do I add Langrit to Claude Code?

Run this command in your terminal: claude mcp add --transport http langrit https://langrit.com/mcp

What are the best alternatives to Langrit?

The closest alternatives to Langrit are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to Langrit

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity