Provides tools for accessing LeetCode submission history, weak area analysis, user stats, and daily challenge data.
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., "@PersonalLeetcodeMCP Analyze my weak areas on LeetCode — my username is @alice_w"
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.
A remote MCP server that connects Claude to your LeetCode data, tracks your practice with a spaced-repetition system, and (optionally) sends scheduled check-in texts so you actually keep up with review.
Tool | Description |
| Recent submissions with status, language, multi-attempt detection |
| Topic-by-topic weak vs. strong breakdown |
| Accepted/submission counts, streaks, ranking percentile |
| Today's daily challenge problem |
| Filter problems by tag and/or difficulty |
| Full statement, constraints, hints, examples for one problem |
| Problems LeetCode tags as related |
| LeetCode's own "what to try next" suggestions |
| Random problem by difficulty/topic/company, framed as a timed interview |
| Record an attempt's outcome, updating its review schedule |
| What's due or overdue for spaced-repetition review |
| Configure check-in frequency (GRIND / MODERATE / BUSY / MINIMAL) and phone number |
| Your tag coverage vs. core FAANG interview topics |
Related MCP server: Interactive LeetCode MCP
UPSTASH_REDIS_REST_URL= UPSTASH_REDIS_REST_TOKEN= LEETCODE_SESSION= # your LeetCode session cookie, for Premium-gated data CSRF_TOKEN= # your LeetCode csrftoken cookie DAILY_CHECK_SECRET= # shared secret protecting /internal/daily-check TETHER_USERNAME= # your LeetCode username (solo-phase, hardcoded)
npm install npm run build npm start
Push to GitHub, then deploy on Render:
Runtime: Docker (Dockerfile is included)
Add all env vars above under the Environment tab
Settings → Connectors → Add custom connector → enter
https://your-deployment-url.com/mcp
Using a free service like cron-job.org, schedule a
daily POST to https://your-deployment-url.com/internal/daily-check with
header x-daily-check-secret: <your DAILY_CHECK_SECRET>.
LeetCode has no official public API. This server uses the same GraphQL
endpoint LeetCode's own frontend uses — it may break if LeetCode changes
their API structure. Authenticated queries (Premium data, company tags)
require a valid LEETCODE_SESSION + CSRF_TOKEN pair from your browser.
This server cannot be deployed
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Pace is a remote MCP server that exposes wearable and fitness data to Claude via the Model Context Protocol. It connects to Garmin, Oura, Whoop, Polar, Fitbit and 20+ devices and provides 15 tools for querying sleep, activity, recovery, and training data. Hosted on Google Cloud Run, OAuth 2.1 authentication, Streamable HTTP transport. Instructions: First you need to create an account at: https://pacetraining.co and connect your wearables. After that you can connect the remote Server via Custom Connector in Claude and OAuth 2.1 Flow startet.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
