This document provides detailed usage examples for the Code-Reasoning MCP Server. These examples demonstrate how to use the sequential thinking capabilities for programming tasks and complex problem-solving.
This example shows a basic sequential thinking process for solving a programming problem:
// Thought 1
{
"thought": "First, let's understand the problem: we need to implement a function that finds duplicate elements in an array.",
"thought_number": 1,
"total_thoughts": 4,
"next_thought_needed": true
}
// Thought 2
{
"thought": "There are multiple approaches we could take: using nested loops (O(n²)), using a hash table (O(n)), or sorting and then finding adjacent duplicates (O(n log n)).",
"thought_number": 2,
"total_thoughts": 4,
"next_thought_needed": true
}
// Thought 3
{
"thought": "Let's implement the hash table approach since it's efficient in terms of time complexity (O(n)). We'll use a Set or Map to track elements we've seen.",
"thought_number": 3,
"total_thoughts": 4,
"next_thought_needed": true
}
// Thought 4
{
"thought": "Here's the JavaScript implementation:\n\nfunction findDuplicates(arr) {\n const seen = new Set();\n const duplicates = new Set();\n \n for (const item of arr) {\n if (seen.has(item)) {\n duplicates.add(item);\n } else {\n seen.add(item);\n }\n }\n \n return Array.from(duplicates);\n}\n\nThis solution is O(n) in time complexity and handles edge cases properly.",
"thought_number": 4,
"total_thoughts": 4,
"next_thought_needed": false
}This example demonstrates how to use sequential thinking to debug a recursive function with a stack overflow issue:
// Thought 1
{
"thought": "The problem is a stack overflow error in a recursive function to calculate Fibonacci numbers. Let's first understand the current implementation.",
"thought_number": 1,
"total_thoughts": 5,
"next_thought_needed": true
}
// Thought 2
{
"thought": "Here's the problematic code:\n\nfunction fibonacci(n) {\n return fibonacci(n - 1) + fibonacci(n - 2);\n}\n\nThe issue is there's no base case, so it recurses infinitely. Also, this is extremely inefficient due to recalculating values repeatedly.",
"thought_number": 2,
"total_thoughts": 5,
"next_thought_needed": true
}
// Thought 3
{
"thought": "Let's fix the base case issue first:\n\nfunction fibonacci(n) {\n if (n <= 0) return 0;\n if (n === 1) return 1;\n return fibonacci(n - 1) + fibonacci(n - 2);\n}\n\nThis prevents infinite recursion, but is still inefficient for large n values.",
"thought_number": 3,
"total_thoughts": 5,
"next_thought_needed": true
}
// Thought 4
{
"thought": "To improve efficiency, we should use memoization to store previously calculated values:\n\nfunction fibonacci(n, memo = {}) {\n if (n <= 0) return 0;\n if (n === 1) return 1;\n if (memo[n]) return memo[n];\n \n memo[n] = fibonacci(n - 1, memo) + fibonacci(n - 2, memo);\n return memo[n];\n}\n\nThis caches results to prevent redundant calculations.",
"thought_number": 4,
"total_thoughts": 5,
"next_thought_needed": true
}
// Thought 5
{
"thought": "For even better performance, we could use an iterative approach instead of recursion:\n\nfunction fibonacci(n) {\n if (n <= 0) return 0;\n if (n === 1) return 1;\n \n let a = 0, b = 1;\n for (let i = 2; i <= n; i++) {\n const temp = a + b;\n a = b;\n b = temp;\n }\n \n return b;\n}\n\nThis iterative solution has O(n) time complexity and constant space complexity, avoiding both stack overflow and inefficiency issues.",
"thought_number": 5,
"total_thoughts": 5,
"next_thought_needed": false
}This example demonstrates how to use thought branching to explore multiple approaches to solving a programming problem:
// Thought 1 (Main path)
{
"thought": "We need to design a system that can efficiently process large batches of data. Let's consider the main approaches.",
"thought_number": 1,
"total_thoughts": 6,
"next_thought_needed": true
}
// Thought 2 (Main path)
{
"thought": "Main Approach: We could use a streaming architecture with message queues for handling data in real-time batches.",
"thought_number": 2,
"total_thoughts": 6,
"next_thought_needed": true
}
// Thought 3 (Branch from Thought 1)
{
"thought": "Alternative Approach: We could also consider batch processing with scheduled ETL jobs instead of real-time processing.",
"thought_number": 3,
"total_thoughts": 6,
"branch_from_thought": 1,
"branch_id": "BatchETL",
"next_thought_needed": true
}
// Thought 3 (Main path)
{
"thought": "For the streaming approach, we'll need components like: data producers, message broker (Kafka/RabbitMQ), stream processors, and data storage.",
"thought_number": 3,
"total_thoughts": 6,
"next_thought_needed": true
}
// Thought 4 (BatchETL branch)
{
"thought": "For batch ETL, we'll need: data extraction jobs, transformation pipelines, data warehousing, and orchestration tools like Airflow.",
"thought_number": 4,
"total_thoughts": 6,
"branch_from_thought": 3,
"branch_id": "BatchETL",
"next_thought_needed": true
}
// Thought 4 (Main path)
{
"thought": "Main approach implementation: 1) Set up Kafka topics, 2) Implement data producers with retry logic, 3) Create stream processors with Kafka Streams, 4) Store in timeseries DB.",
"thought_number": 4,
"total_thoughts": 6,
"next_thought_needed": true
}
// Thought 5 (BatchETL branch)
{
"thought": "The batch approach is simpler and more cost-effective for this use case. Implementing with: 1) Daily data dumps, 2) Spark processing, 3) Data warehouse loading.",
"thought_number": 5,
"total_thoughts": 6,
"branch_from_thought": 4,
"branch_id": "BatchETL",
"next_thought_needed": false
}
// Thought 5 (Main path)
{
"thought": "After comparing both approaches, the streaming architecture is preferred due to real-time requirements, despite higher complexity and cost.",
"thought_number": 5,
"total_thoughts": 6,
"next_thought_needed": false
}This example demonstrates how to use thought revision to correct errors in reasoning:
// Thought 1
{
"thought": "I need to implement a sort algorithm. Based on requirements, quicksort seems appropriate due to average case O(n log n) performance.",
"thought_number": 1,
"total_thoughts": 4,
"next_thought_needed": true
}
// Thought 2
{
"thought": "Here's a basic quicksort implementation in Python:\n\ndef quicksort(arr):\n if len(arr) <= 1:\n return arr\n pivot = arr[0]\n left = [x for x in arr[1:] if x < pivot]\n right = [x for x in arr[1:] if x >= pivot]\n return quicksort(left) + [pivot] + quicksort(right)",
"thought_number": 2,
"total_thoughts": 4,
"next_thought_needed": true
}
// Thought 3 (Revision of Thought 1)
{
"thought": "On second thought, I overlooked the fact that the data might be already partially sorted, which is quicksort's worst-case scenario (O(n²)). Also, stability is required. Mergesort would be a better choice since it guarantees O(n log n) regardless of input and is stable.",
"thought_number": 3,
"total_thoughts": 5,
"is_revision": true,
"revises_thought": 1,
"next_thought_needed": true
}
// Thought 4 (Revision of Thought 2)
{
"thought": "Let's implement mergesort instead:\n\ndef mergesort(arr):\n if len(arr) <= 1:\n return arr\n \n mid = len(arr) // 2\n left = mergesort(arr[:mid])\n right = mergesort(arr[mid:])\n \n return merge(left, right)\n\ndef merge(left, right):\n result = []\n i = j = 0\n \n while i < len(left) and j < len(right):\n if left[i] <= right[j]: # Note: <= preserves stability\n result.append(left[i])\n i += 1\n else:\n result.append(right[j])\n j += 1\n \n result.extend(left[i:])\n result.extend(right[j:])\n return result",
"thought_number": 4,
"total_thoughts": 5,
"is_revision": true,
"revises_thought": 2,
"next_thought_needed": true
}
// Thought 5
{
"thought": "The mergesort implementation meets all requirements: O(n log n) worst-case time complexity, stability, and works well with the expected data patterns. The trade-off is O(n) extra space, but this is acceptable given the reliability benefits.",
"thought_number": 5,
"total_thoughts": 5,
"next_thought_needed": false
}To use the code-reasoning server with Claude Desktop, you'll need to configure Claude Desktop to use the server.
// claude_desktop_config.json
{
"mcpServers": {
"code-reasoning": {
"command": "code-reasoning",
"args": []
}
}
}// claude_desktop_config.json
{
"mcpServers": {
"code-reasoning": {
"command": "code-reasoning",
"args": ["--debug"]
}
}
}When using Claude Desktop with the code-reasoning server, you can use the sequential thinking capability by asking Claude to reason step by step. The current tool description is:
🧠 A reflective problem-solving tool with sequential thinking.
• Break down tasks into numbered thoughts that can BRANCH (🌿) or REVISE (🔄) until a conclusion is reached.
• Always set 'next_thought_needed' = false when no further reasoning is needed.
✅ Recommended checklist every 3 thoughts:
1. Need to BRANCH? → set 'branch_from_thought' + 'branch_id'.
2. Need to REVISE? → set 'is_revision' + 'revises_thought'.
3. Scope changed? → bump 'total_thoughts'.
✍️ End each thought with: "What am I missing?"
Example prompts to use with Claude:
Please help me design a simple REST API for a todo application. Use code-reasoning to break down the design process into steps.
Or more specifically for code-related tasks:
Please analyze this algorithm implementation and identify any bugs or inefficiencies. Use code-reasoning to break down your analysis step by step.
For VS Code integration, you can configure the MCP server in your VS Code settings.
// settings.json or .vscode/mcp.json
{
"mcp": {
"servers": {
"code-reasoning": {
"command": "code-reasoning",
"args": ["--debug"]
}
}
}
}To enable detailed logging, use the --debug flag:
code-reasoning --debugStarting Code-Reasoning MCP Server (streamlined v0.5.0)... {
"logLevel": "INFO",
"debug": true,
"pid": 12345
}
Code Reasoning Server logic handler initialized {
"config": {
"maxThoughtLength": 20000,
"timeoutMs": 30000,
"maxThoughts": 20,
"logLevel": "INFO",
"debug": true
}
}
Received ListTools request
💭 Thought 1/5
---
First, let's understand the problem: we need to design a simple calculator function.
---
Thought processed successfully {
"thought_number": 1,
"is_revision": false,
"branch_id": null,
"next_thought_needed": true,
"processingTimeMs": 5
}
{
"mcpServers": {
"code-reasoning": {
"command": "code-reasoning",
"args": ["--debug"]
},
"another-server": {
"command": "another-command",
"args": []
}
},
"defaultModel": "claude-3-7-sonnet",
"sessionDefaults": {
"enableMultiModal": true
}
}{
"editor.fontFamily": "Fira Code, monospace",
"editor.fontSize": 14,
"mcp": {
"servers": {
"code-reasoning": {
"command": "code-reasoning",
"args": ["--debug"]
}
}
}
}{
"servers": {
"code-reasoning": {
"command": "code-reasoning",
"args": ["--debug"]
}
}
}