my-sequential-thinking
MCP server from ZannyTornadoCoding/my-sequential-thinking-mcp-server
claude mcp add --transport stdio zannytornadocoding-my-sequential-thinking-mcp-server node index.js
How to use
This MCP server provides structured sequential thinking capabilities that integrate with Cline's Memory Bank. It enables you to create and manage thinking chains, add steps with reasoning and evidence, validate connections between steps, and visualize the chain flow. You can also save complete thinking chains to Memory Bank, load them back for continuation, and search for related chains using keywords and tags. Tools like create_thinking_chain, add_thinking_step, and generate_visualization help you build a traceable reasoning process, while save_to_memory and load_from_memory facilitate persistent storage and retrieval within Memory Bank. The system supports various thinking styles (Analytical, Creative, Critical, Systems, First-Principles, Divergent, Convergent, Inductive, Deductive) and ships with templates to kickstart reasoning (e.g., First Principles Analysis, Systems Thinking Analysis).
How to install
Prerequisites:
- Node.js v14 or later installed on your machine
- Git to clone the repository
Installation steps:
- Clone the repository: git clone <repository-url>
- Navigate to the project directory: cd <repository-directory>
- Install dependencies: npm install
- Start the MCP server: node index.js
Verification:
- If the server starts successfully, it will listen for MCP connections and announce readiness in the console. You can then connect to it using your MCP client (e.g., Claude/Cline) and begin issuing MCP tool calls such as create_thinking_chain, add_thinking_step, and generate_visualization.
Additional notes
Tips and considerations:
- Ensure Node.js version compatibility (v14+ recommended) to avoid runtime issues.
- Memory Bank integration requires proper configuration on the Memory Bank side; ensure credentials and endpoints are available if you plan to save or load chains.
- When using generate_visualization, choose a format (mermaid, json, or text) that best fits your workflow; mermaid is convenient for rendering flow diagrams.
- Use tags strategically to organize chains by Thinking Type, Domain, Complexity, and Status for easier retrieval via search.
- If you encounter connection issues, check that the MCP server process has the necessary network access and that any required environment variables for Memory Bank are defined.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.