LeetCode Tracker MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LEETCODE_SESSION | No | Cookie сессии, нужна только для импорта всей истории | |
| LEETCODE_USERNAME | No | Username по умолчанию | |
| LEETCODE_CSRF_TOKEN | No | Cookie csrftoken, используется вместе с сессией | |
| LEETCODE_TRACKER_DATA | No | Путь к файлу данных, по умолчанию ~/.leetcode-tracker/data.json |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| sync_progressA | Import accepted submissions from LeetCode and record today's progress snapshot. Without a session LeetCode exposes only the latest 20 accepted submissions, so sync regularly. |
| get_progressB | Show solved counts by difficulty, ranking, streak, recent activity, weekly and monthly gains, goals and due reviews. |
| log_attemptA | Record a practice attempt with time, confidence and notes, then schedule the next spaced-repetition review. |
| get_problem_historyB | Show one problem's details, attempts, notes and review schedule. |
| list_tracked_problemsB | List locally tracked problems, most recently attempted first. |
| get_due_reviewsA | List problems due for spaced-repetition review, most overdue first. |
| analyze_topicsC | Find the least practiced topics at each level and the topics with the highest local failure rate. |
| set_goalB | Set a target for the total number of solved problems in a category. A target of 0 removes that goal. |
| get_daily_challengeA | Show today's LeetCode daily challenge and whether it was solved before. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a distinct action-resource focus: listing tracked problems, listing due reviews, single-problem history, aggregate progress, topic analysis, syncing, logging, goal setting, and the daily challenge. The only mild overlap is between get_due_reviews and get_progress, which also reports due reviews, and between list_tracked_problems and get_problem_history, but the singular/plural and 'history' distinction makes boundaries clear enough.
Every tool follows a clean verb_noun snake_case pattern (list_*, get_*, log_*, sync_*, set_*, analyze_*). No camelCase or vague single-word verbs; the pattern is fully predictable.
Nine tools is well within the ideal 3-15 range and every tool maps to a real workflow: tracking, spaced repetition, syncing, stats, goals, and daily challenge. Nothing appears redundant or padded.
Core lifecycle is covered—sync submissions, log attempts, schedule reviews, view history, analyze topics, set goals, and fetch the daily challenge. Minor gaps exist: no way to edit or delete a logged attempt, and no explicit tool to selectively untrack or add a problem outside sync/log_attempt.