dsa-tracker-mcp

mcp-name: io.github.ashmitrrr/dsa-tracker-mcp-server

This is an MCP server for tracking your progress through your DSA questions and comes loaded with a default list of Neetcode 150 (any custom DSA problem list can be switched per user) with built-in spaced repetition. Built with FastMCP and SQLite.

Talk to it naturally from Claude: "what should I work on next", "log that I solved Two Sum, confidence 4, took 12 minutes", "how's my progress", "show me my history on Contains Duplicate".

Features

• Spaced repetition — problems you struggle with come back sooner, problems you nail come back later. Schedule is based on how you rated each attempt (gave up / struggled / solved) and your confidence (1-5).
• List-agnostic — ships with the full NeetCode 150 (150 problems, 18 categories) but can load any custom problem list via a JSON file.
• Fuzzy matching — log an attempt with a loosely-typed problem name ("two sum", "contains dupe") and it'll match the right problem.
• Stats & streaks — solved counts, per-category breakdown, daily streak, total time spent.

Tools

Resources

• dsa://progress — current progress snapshot
• dsa://problem-list — full list of tracked problems

Prompts

• daily_review — generates a daily review session based on what's due
• explain_pattern(category) — explains the core pattern/approach for a given category

Installation

git clone https://github.com/ashmitrrr/dsa-tracker-mcp.git
cd dsa-tracker-mcp
python3 -m venv .venv
source .venv/bin/activate   # on Windows: .venv\Scripts\activate
pip install -r requirements.txt

Configuration

Claude Desktop

Add to your claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "dsa-tracker": {
      "command": "/absolute/path/to/dsa-tracker-mcp/.venv/bin/python",
      "args": ["/absolute/path/to/dsa-tracker-mcp/server.py"]
    }
  }
}

Restart Claude Desktop completely after saving.

Environment variables (optional)

Custom problem list format

[
  {
    "name": "Two Sum",
    "category": "Arrays & Hashing",
    "difficulty": "Easy",
    "url": "https://leetcode.com/problems/two-sum/"
  }
]

url and difficulty are optional and will be auto-filled where possible. order_index is assigned automatically based on list order.

Spaced repetition logic

get_next_problem prioritizes overdue reviews before suggesting new problems.

Example prompts

• "What should I work on next?"
• "I just solved Valid Anagram, confidence 5, took 6 minutes, log it"
• "How's my progress on Trees?"
• "Show me my history on Two Sum"
• "Give me a daily review"

License

MIT — see LICENSE.