Interactive Leetcode MCP

Current project is under active development and may not work perfectly

- 🔐AI-guided authentication- Claude walks you through one-time credential setup
- 🎓Learning-guided mode- AI provides hints before solutions to maximize learning
- 📝Solution submission- Submit code and get instant results
- 💬Conversational workflow- Practice naturally with Claude Code
- 🌍Multi-language support- Java, Python, C++, JavaScript, TypeScript, and more
- 📊Detailed feedback- Runtime stats, memory usage, failed test cases
- 📚Problem data- Descriptions, constraints, examples, editorial solutions
- 👤User tracking- Profile data, submission history, contest rankings

- Node.js v20.x or above
- LeetCode account
- Any modern web browser (Chrome, Firefox, Safari, Edge, etc.)

npm install -g @sperekrestova/interactive-leetcode-mcp interactive-leetcode-mcp --version interactive-leetcode-mcp --help

You can also run the package without installing it globally:

npx -y @sperekrestova/interactive-leetcode-mcp@latest --version

git clone https://github.com/SPerekrestova/interactive-leetcode-mcp.git cd interactive-leetcode-mcp npm install && npm run build npm link

Use this to verify the published npm package from a clean directory without any LeetCode credentials:

mkdir leetcode-mcp-smoke cd leetcode-mcp-smoke npm init -y npm install @sperekrestova/interactive-leetcode-mcp npx --no-install interactive-leetcode-mcp --version npx --no-install interactive-leetcode-mcp --help

Those commands confirm that Node can install the package and expose the CLI binary. For actual MCP server validation, use an integration test that connects over stdio and completes the MCP handshake.

claude mcp add --transport stdio leetcode -- npx -y @sperekrestova/interactive-leetcode-mcp@latest

Or add to your MCP configuration file (~/.config/claude-code/mcp.json) or (~/Library/Application Support/Claude/claude_desktop_config.json):

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

{ "mcpServers": { "leetcode": { "command": "node", "args": ["/path/to/this/project/interactive-leetcode-mcp/build/index.js"] } } }

You: "I want to practice two-sum" Claude: [Fetches problem and creates working file]

You: "Give me a hint" Claude: [Provides contextual guidance based on your code]

You: "Submit my solution" Claude: "🎉 Accepted! Runtime: 2ms (beats 95.3%)"

- Returns the server usage guide, learning flow, authentication flow, and submission language map
- Call this at the start of a LeetCode practice session

- Initiates authentication flow
- Opens browser to LeetCode login (when possible)
- Returns structured instructions for AI agent to guide you
- No parameters required

- Checks if you're authenticated
- Returns username and credential age
- Warns if credentials may expire soon
- No parameters required

- Fetch today's daily coding challenge

- Get detailed problem information by slug
- Parameters:titleSlug(e.g., "two-sum")

- Search problems by difficulty, tags, keywords
- Supports filtering and pagination

- Opens or resumes a tutoring session for a problem
- Parameters:titleSlug, optionallanguage
- Required before problem-specific hint and solution tools

- Advances progressive hint levels for the active session
- Parameters:titleSlug
- Unlocks community solution tools after the final hint level

- Shows current hint level and session metadata
- Parameters:titleSlug

- Resets hint progress for a problem
- Parameters:titleSlug

- Reports which local runtimes are available for supported languages

- Runs user code against sample tests in a local subprocess sandbox
- Parameters:titleSlug,language,code, optionaltimeoutMs

- Lists community/editorial solution articles for a problem
- Parameters:questionSlug, optionallimit,skip,orderBy,userInput,tagSlugs
- Requires the session to reach the solution-unlocked hint level

- Fetches a specific solution article
- Parameters:topicId,titleSlug
- Requires the session to reach the solution-unlocked hint level

- Submit code and get real-time results
- Parameters:problemSlug,code,language
- Returns: acceptance status, runtime, memory, or failed test case

- Get authenticated user's status/profile summary

- Get solved/attempted progress for a problem

The Interactive LeetCode MCP includes AI agent guidance through MCP Prompts to create a better learning experience.

Workspace Setup:When learning mode is active, Claude will:

- Create a workspace file named{problem-slug}.{extension}
- Paste the code template into the file
- Set up proper naming conventions (e.g., Java class names)

Learning-Guided Mode:When active, Claude follows these guidelines:

- Provides progressive hints (4 levels) before revealing solutions
- Asks guiding questions about approach and complexity
- Encourages independent problem-solving
- Only shows complete solutions when explicitly requested

Problem Workflow:Guides you through the complete cycle:
- Understand the problem
- Plan the approach
- Set up workspace
- Implement with hints
- Optimize and analyze complexity
- Submit and review results

To activate learning mode, tell Claude you want to practice with guidance — for example, "Let's practice in learning mode" or "I want to learn two-sum with hints." Once active:
- Callget_startedto load the server's usage guide
- Fetch a problemwithget_daily_challenge,search_problems, orget_problem
- Open a sessionwithstart_problem
- Ask for hintsviarequest_hintrather than jumping straight to solutions
- Implement your solutionwith progressive guidance
- Request the solutiononly after the final hint level or when you want to compare with an optimal approach

To test the MCP server as a black-box MCP client without live LeetCode traffic:

This builds the server, spawnsbuild/index.jsover stdio, connects with the MCP SDK client, uses an isolatedHOME, serves LeetCode responses from fixtures, and drives a user-like flow throughrunner_doctor,start_problem,request_hint,run_local_tests, andget_session_state.

SeeDOGFOOD_TESTING.mdfor the full workflow and a copy-paste prompt for local Claude/agent dogfood testing.

/plugin marketplace add SPerekrestova/interactive-leetcode-mcp /plugin install interactive-leetcode-mcp@interactive-leetcode-mcp

/interactive-leetcode-mcp:interactive-leetcode-mcp

The skill is also published onClawHubfor use with OpenClaw-compatible agents.

- NPM Package
- Report Issues
- MCP Documentation

AI-to-AI code review platform — Claude, Codex, and Gemini cross-check each other via MCP, REST API, and CLI for consensus-based results.