Sequential Thinking MCP server

The Enhanced Sequential Thinking MCP Server implements the Model Context Protocol to provide structured problem-solving capabilities through sequential thought steps. It helps break down complex problems into stages while tracking progress, categorizing thoughts, and generating summaries of the thinking process.

Installation

Prerequisites

• Python 3.11 or higher
• UV package manager

Setup Steps

1. Create and activate a virtual environment:

# Create virtual environment
uv venv

# Activate the environment (Windows)
.venv\Scripts\activate

# Activate the environment (Unix/macOS)
source .venv/bin/activate

2. Install the package and its dependencies:

# Install in development mode
uv pip install -e .

3. Run the server:

cd mcp_sequential_thinking
uv run server.py

Claude Desktop Integration

To integrate the server with Claude Desktop, add the following configuration to your Claude Desktop configuration file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sequential-thinking": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\path\\to\\your\\mcp-sequential-thinking\\mcp_sequential_thinking",
        "run",
        "server.py"
      ]
    }
  }
}

Be sure to replace C:\\path\\to\\your\\mcp-sequential-thinking\\mcp_sequential_thinking with the actual path to your installation directory.

Using the MCP Server

The server provides two main tools that can be accessed through the Model Context Protocol:

Sequential Thinking Tool

The primary tool processes individual thoughts as part of a sequential thinking process.

Parameters:

• thought (str): The content of the current thought
• thought_number (int): The sequence number of the current thought
• total_thoughts (int): The total number of thoughts expected
• next_thought_needed (bool): Whether another thought is needed
• stage (str): The current stage of thinking (Problem Definition, Analysis, Ideation, Evaluation, Conclusion)
• is_revision (bool, optional): Whether this revises previous thinking
• revises_thought (int, optional): Which thought is being reconsidered
• branch_from_thought (int, optional): Branching point thought number
• branch_id (str, optional): Branch identifier
• needs_more_thoughts (bool, optional): If more thoughts are needed
• score (float, optional): Score for the thought (0.0 to 1.0)
• tags (List[str], optional): List of tags for categorizing the thought

Get Thinking Summary Tool

This tool generates a comprehensive summary of the entire thinking process.

Troubleshooting

If you encounter issues with the server, try these solutions:

• Server Connection Issues:
  • Verify the paths in your claude_desktop_config.json file
  • Check Claude Desktop logs at %APPDATA%\Claude\logs
  • Try starting the server manually to see if there are any error messages

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.