# io.github.SPerekrestova/interactive-leetcode-mcp (npm · @sperekrestova/interactive-leetcode-mcp)

Interactive LeetCode MCP server with authorization and solution submission capabilities

- Trust score: 82/100 (high trust)
- Change this week: +29
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@sperekrestova/interactive-leetcode-mcp`: 82/100 (this document), [markdown](https://verifymcp.io/servers/sperekrestova-interactive-leetcode-mcp/sperekrestova-interactive-leetcode-mcp.md), [page](https://verifymcp.io/servers/sperekrestova-interactive-leetcode-mcp/sperekrestova-interactive-leetcode-mcp)

## Channel facts

- Registry: `npm`
- Package: `@sperekrestova/interactive-leetcode-mcp`
- Version: `3.2.5`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 88/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (133 of 134), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (133 of 134), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to SPerekrestova/interactive-leetcode-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 39 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 2680 tokens (~99/item across 27 items; 24 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add sperekrestova-interactive-leetcode-mcp -- npx -y @sperekrestova/interactive-leetcode-mcp
```

### Codex

```bash
codex mcp add sperekrestova-interactive-leetcode-mcp -- npx -y @sperekrestova/interactive-leetcode-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sperekrestova-interactive-leetcode-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@sperekrestova/interactive-leetcode-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sperekrestova-interactive-leetcode-mcp --command npx --arg -y --arg @sperekrestova/interactive-leetcode-mcp
```

### Hermes

```yaml
mcp_servers:
  sperekrestova-interactive-leetcode-mcp:
    command: "npx"
    args: ["-y", "@sperekrestova/interactive-leetcode-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "sperekrestova-interactive-leetcode-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sperekrestova/interactive-leetcode-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 81, +55)

- [security improvement] Provenance: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] The attested source repository moved: SPerekrestova/interactive-leetcode-mcp
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 26, −9)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 35, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (24)

### `get_started` (~48 tokens)

Returns the usage guide for this MCP server: which prompts to invoke and when, session flow, auth flow, and submission language map. Call this at the start of any LeetCode practice session.

### `get_daily_challenge` (~55 tokens)

Retrieves today's LeetCode Daily Challenge problem with complete details, including problem description, constraints, and examples. After fetching, invoke the leetcode_learning_mode and leetcode_problem_workflow prompts before helping the user work on it.

### `get_problem` (~94 tokens)

Retrieves details about a specific LeetCode problem, including its description, examples, constraints, and related information. After fetching, invoke the leetcode_learning_mode and leetcode_problem_workflow prompts before helping the user work on it.

Input parameters:

- `titleSlug` (string, required): The URL slug/identifier of the problem (e.g., 'two-sum', 'add-two-numbers') as it appears in the LeetCode URL

### `search_problems` (~164 tokens)

Searches for LeetCode problems based on multiple filter criteria including categories, tags, difficulty levels, and keywords, with pagination support

Input parameters:

- `category` (string): Problem category filter (e.g., 'algorithms', 'database', 'shell') to narrow down the problem domain
- `difficulty` (string): Problem difficulty level filter to show only problems of a specific difficulty
- `limit` (number): Maximum number of problems to return in a single request (for pagination)
- `offset` (number): Number of problems to skip (for pagination)
- `searchKeywords` (string): Keywords to search in problem titles and descriptions
- `tags` (array): List of topic tags to filter problems by (e.g., ['array', 'dynamic-programming', 'tree'])

### `get_user_profile` (~46 tokens)

Retrieves profile information about a LeetCode user, including user stats, solved problems, and profile details

Input parameters:

- `username` (string, required): LeetCode username to retrieve profile information for

### `get_recent_submissions` (~68 tokens)

Retrieves a user's recent submissions on LeetCode Global, including both accepted and failed submissions with detailed metadata

Input parameters:

- `limit` (number): Maximum number of submissions to return (optional, defaults to server-defined limit)
- `username` (string, required): LeetCode username to retrieve recent submissions for

### `get_recent_ac_submissions` (~72 tokens)

Retrieves a user's recent accepted (AC) submissions on LeetCode Global, focusing only on successfully completed problems

Input parameters:

- `limit` (number): Maximum number of accepted submissions to return (optional, defaults to server-defined limit)
- `username` (string, required): LeetCode username to retrieve recent accepted submissions for

### `get_user_status` (~34 tokens)

Retrieves the current user's status on LeetCode, including login status, premium membership details, and user information (requires authentication)

### `get_problem_submission_report` (~54 tokens)

Retrieves detailed information about a specific LeetCode submission by its ID, including source code, runtime stats, and test results (requires authentication)

Input parameters:

- `id` (number, required): The numerical submission ID to retrieve detailed information for

### `get_problem_progress` (~150 tokens)

Retrieves the current user's problem-solving status with filtering options, including detailed solution history for attempted or solved questions (requires authentication)

Input parameters:

- `difficulty` (array): Filter by difficulty levels as an array (e.g., ['EASY', 'MEDIUM', 'HARD']); if not provided, questions of all difficulty levels will be returned
- `limit` (number): The maximum number of questions to return in a single request
- `offset` (number): The number of questions to skip for pagination purposes
- `questionStatus` (string): Filter by question status: 'ATTEMPTED' for questions that have been tried but not necessarily solved, 'SOLVED' for questions that have been successfully completed

### `get_all_submissions` (~118 tokens)

Retrieves a paginated list of the current user's submissions for a specific problem or all problems on LeetCode Global, with detailed submission metadata (requires authentication)

Input parameters:

- `limit` (number): Maximum number of submissions to return per page (typically defaults to 20 if not specified)
- `offset` (number): Number of submissions to skip for pagination purposes
- `questionSlug` (string): Optional problem identifier (slug) to filter submissions for a specific problem (e.g., 'two-sum'); if omitted, returns submissions across all problems

### `get_user_contest_ranking` (~83 tokens)

Retrieves a user's contest ranking information on LeetCode, including overall ranking, participation history, and performance metrics across contests

Input parameters:

- `attended` (boolean): Whether to include only the contests the user has participated in (true) or all contests (false); defaults to true
- `username` (string, required): LeetCode username to retrieve contest ranking information for

### `start_problem` (~110 tokens)

Opens (or resumes) a tutoring session for a LeetCode problem. Must be called before request_hint, list_problem_solutions, or get_problem_solution. Idempotent: re-running on a slug the user is already mid-way through preserves their hint progress.

Input parameters:

- `language` (string): Optional: the language the user is solving in. Recorded on the session for future workspace / runner phases.
- `titleSlug` (string, required): The URL slug of the problem (e.g., 'two-sum').

### `request_hint` (~79 tokens)

Advances the hint level for an active session and returns the next hint. Levels: 1 clarification → 2 approach → 3 implementation sketch → 4 solution unlock. The community-solutions tools become callable only after this has been driven to level 4.

Input parameters:

- `titleSlug` (string, required): The URL slug of the problem the user is working on.

### `get_session_state` (~52 tokens)

Returns the persisted session for a problem, or null if the user has not called start_problem for it. Useful for restoring context after a restart.

Input parameters:

- `titleSlug` (string, required): The URL slug of the problem.

### `reset_session` (~53 tokens)

Resets the tutoring session for a problem back to hint level 0. Use when the user wants to re-attempt the problem from scratch.

Input parameters:

- `titleSlug` (string, required): The URL slug of the problem to reset.

### `list_problem_solutions` (~223 tokens)

Retrieves community solution metadata (topicIds) for a problem. GATED: rejects with HINT_LEVEL_TOO_LOW unless the active session for the slug has reached the maximum hint level. Drive the user through request_hint until that level is reached.

Input parameters:

- `limit` (integer): Maximum number of solutions to return per request. Default 10. Must be a positive integer.
- `orderBy` (string): Sorting criteria. 'HOT' is LeetCode's default (recency × popularity), 'MOST_VOTES' = upvotes, 'MOST_RECENT' = newest.
- `questionSlug` (string, required): The URL slug of the problem (e.g., 'two-sum').
- `skip` (integer): Number of solutions to skip before collecting results. Used with `limit` for pagination.
- `tagSlugs` (array): Tag slugs to filter by (languages or algorithm tags). Solutions must match at least one tag.
- `userInput` (string): Search term to filter solutions by title, content, or author name. Case-insensitive.

### `get_problem_solution` (~107 tokens)

Retrieves the full content of a specific community solution. GATED: rejects with HINT_LEVEL_TOO_LOW unless the session for `titleSlug` has reached the maximum hint level. Pass the topicId returned by `list_problem_solutions`.

Input parameters:

- `titleSlug` (string, required): The URL slug of the problem the solution belongs to. Required to verify the session has reached the unlock level.
- `topicId` (string, required): The unique topic ID of the solution, returned by list_problem_solutions.

### `run_local_tests` (~212 tokens)

Runs the user's code locally in an isolated subprocess, captures stdout / stderr / exit code, and updates the session's lastLocalRunPassed flag. Use this in the inner loop instead of submit_solution — it costs no LeetCode submission and turns around in seconds. The agent is responsible for including test invocations (e.g. `print(Solution().twoSum([2,7,11,15], 9))`) in the code passed in. Currently runnable: python3, go, and java.

Input parameters:

- `code` (string, required): Complete source code to execute. Should include test invocations that print results / raise on failure.
- `language` (string, required): Language to execute as. Currently runnable: python3, go, java. Other LeetCode languages remain valid for submit_solution.
- `timeoutMs` (integer): Optional wall-clock budget in milliseconds. Defaults are language-specific.
- `titleSlug` (string, required): The URL slug of the problem (must match an active session opened with start_problem).

### `runner_doctor` (~66 tokens)

Reports which language runtimes (python3, go, java) and OS sandbox tools (bwrap, firejail, sandbox-exec) are detected on this host. Useful for diagnosing 'LANGUAGE_RUNTIME_NOT_FOUND' errors and confirming whether run_local_tests will be sandboxed.

### `start_leetcode_auth` (~49 tokens)

Initiates LeetCode authentication flow. Opens browser to LeetCode login (if possible) and provides instructions for the AI agent to guide the user through manual credential extraction from browser DevTools.

### `save_leetcode_credentials` (~86 tokens)

Validates and saves LeetCode credentials provided by the user. Validates credentials by making a test API call to LeetCode, then securely stores them for future authenticated requests.

Input parameters:

- `csrftoken` (string, required): CSRF token from LeetCode cookies (csrftoken)
- `session` (string, required): Session token from LeetCode cookies (LEETCODE_SESSION)

### `check_auth_status` (~34 tokens)

Checks if LeetCode credentials exist and are still valid. Returns authentication status, username if authenticated, and credential age information.

### `submit_solution` (~121 tokens)

Submit a solution to a LeetCode problem and get results. Returns acceptance status, runtime/memory stats, or failed test case details. When LEETCODE_MCP_STRICT_MODE=1 is set, requires `run_local_tests` to have last passed for the problem first — saves real LeetCode submissions for solutions that pass examples locally.

Input parameters:

- `code` (string, required): The solution code to submit
- `language` (string, required): Programming language for the solution
- `problemSlug` (string, required): The problem slug (e.g., "two-sum")

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sperekrestova-interactive-leetcode-mcp/sperekrestova-interactive-leetcode-mcp#diagnostics

## Score history

- 2026-08-03: 82
- 2026-08-02: 81
- 2026-08-01: 26
- 2026-07-31: 35
- 2026-07-29: 53
- 2026-07-28: 53
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/@sperekrestova/interactive-leetcode-mcp
- Socket report: https://socket.dev/npm/package/@sperekrestova/interactive-leetcode-mcp
- Repository: https://github.com/SPerekrestova/interactive-leetcode-mcp
- Changelog RSS feed: https://verifymcp.io/servers/sperekrestova-interactive-leetcode-mcp/sperekrestova-interactive-leetcode-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sperekrestova-interactive-leetcode-mcp/sperekrestova-interactive-leetcode-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sperekrestova-interactive-leetcode-mcp/sperekrestova-interactive-leetcode-mcp