Sequential Thinking MCP server

The MCP Sequential Thinking Tools server helps break down complex problems into steps while recommending appropriate tools for each stage. It analyzes your thought process and suggests which Model Context Protocol (MCP) tools would be most effective, including confidence scores and rationales for each recommendation.

Features

• 🤔 Dynamic problem-solving through sequential thoughts
• 🔄 Flexible thinking process that adapts as you progress
• 🌳 Support for branching and revision of thoughts
• 🛠️ Intelligent tool recommendations for each step
• 📊 Confidence scoring for tool suggestions
• 🔍 Detailed rationale for tool recommendations
• 📝 Step tracking with expected outcomes
• 🔄 Progress monitoring with previous and remaining steps
• 🎯 Alternative tool suggestions for each step

Installation

Using npm

You can install the server globally:

npm install -g mcp-sequentialthinking-tools

Or run it directly without installation:

npx mcp-sequentialthinking-tools

Configuration

The server needs to be configured in your MCP client settings. Choose the appropriate configuration method for your environment:

Cline Configuration

Add this to your Cline MCP settings:

{
    "mcpServers": {
        "mcp-sequentialthinking-tools": {
            "command": "npx",
            "args": ["-y", "mcp-sequentialthinking-tools"]
        }
    }
}

Claude Desktop with WSL Configuration

For Windows Subsystem for Linux (WSL) environments, add this to your Claude Desktop configuration:

{
    "mcpServers": {
        "mcp-sequentialthinking-tools": {
            "command": "wsl.exe",
            "args": [
                "bash",
                "-c",
                "source ~/.nvm/nvm.sh && /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-sequentialthinking-tools"
            ]
        }
    }
}

Make sure to replace /home/username/.nvm/versions/node/v20.12.1/bin/npx with your actual Node.js path in WSL.

Usage

The server implements an MCP tool called sequentialthinking_tools with the following parameters:

Required Parameters

• thought (string): Your current thinking step
• next_thought_needed (boolean): Whether another thought step is needed
• thought_number (integer): Current thought number
• total_thoughts (integer): Estimated total thoughts needed

Optional Parameters

• is_revision (boolean): Whether this revises previous thinking
• revises_thought (integer): Which thought is being reconsidered
• branch_from_thought (integer): Branching point thought number
• branch_id (string): Branch identifier
• needs_more_thoughts (boolean): If more thoughts are needed
• current_step (object): Current step recommendation with:
  • step_description: What needs to be done
  • recommended_tools: Array of tool recommendations with confidence scores
  • expected_outcome: What to expect from this step
  • next_step_conditions: Conditions for next step
• previous_steps (array): Steps already recommended
• remaining_steps (array): High-level descriptions of upcoming steps

Example Usage

Here's an example of the server's response format:

{
    "thought": "Initial research step to understand what universal reactivity means in Svelte 5",
    "current_step": {
        "step_description": "Gather initial information about Svelte 5's universal reactivity",
        "expected_outcome": "Clear understanding of universal reactivity concept",
        "recommended_tools": [
            {
                "tool_name": "search_docs",
                "confidence": 0.9,
                "rationale": "Search Svelte documentation for official information",
                "priority": 1
            },
            {
                "tool_name": "tavily_search",
                "confidence": 0.8,
                "rationale": "Get additional context from reliable sources",
                "priority": 2
            }
        ],
        "next_step_conditions": [
            "Verify information accuracy",
            "Look for implementation details"
        ]
    },
    "thought_number": 1,
    "total_thoughts": 5,
    "next_thought_needed": true
}

The server tracks your progress through multiple thoughts and supports:

• Creating branches to explore different approaches
• Revising previous thoughts with new information
• Maintaining context across multiple steps
• Suggesting next steps based on current findings

Advanced Features

Branching

To explore an alternative approach, use the branch_from_thought and branch_id parameters to create a new branch from a specific thought.

Revisions

When you need to reconsider a previous thought, use is_revision and revises_thought parameters to indicate which thought you're revising.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.