MAXential Thinking

Provides structured, persistent, and parallel reasoning for AI workflows through branching thought chains and exportable results.

typescript

2

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "bam-devcrew-maxential-thinking-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@bam-devcrew/maxential-thinking-mcp"
      ],
      "env": {
        "MAXENTIAL_LOG_FILE": "/var/log/maxential.log"
      }
    }
  }
}

MAXential Thinking MCP Server provides structured, persistent, and parallel reasoning capabilities for autonomous AI workflows. It enables you to explore multiple thought-chains, navigate back through reasoning, and export or visualize the full thinking process for documentation and handoffs.

How to use

You run the MAXential Thinking MCP server through an MCP client, then interact with it using the exposed tools to add thoughts, branch reasoning paths, navigate history, and visualize your thinking. Start new thinking chains, create branches to explore alternatives, tag ideas for semantic organization, and export your complete reasoning as Markdown or JSON for your records.

How to install

Prerequisites: you need Node.js installed on your system, and a compatible MCP client to connect to the server. The simplest path is to run the server locally via the provided runtime command or to use the prebuilt MCP via npx.

# Option A: use the prebuilt MCP via npx (recommended for quick start)
npx -y @bam-devcrew/maxential-thinking-mcp

# Option B: run from source after building
git clone https://github.com/BAM-DevCrew/MAXential-Thinking-MCP.git
cd MAXential-Thinking-MCP
npm install
npm run build
# Start the server with the built entry point
node dist/src/index.js

Configuration basics

Configure the MCP in your client to point to the server you plan to use. Below are representative configurations shown in examples. Use the appropriate one for your environment.

{
  "mcpServers": {
    "maxential-thinking": {
      "command": "npx",
      "args": ["-y", "@bam-devcrew/maxential-thinking-mcp"]
    }
  }
}

Starting from source

If you built the server from source, configure the runtime to run the built entry point as shown.

{
  "mcpServers": {
    "maxential-thinking": {
      "command": "node",
      "args": ["/path/to/MAXential-Thinking-MCP/dist/src/index.js"]
    }
  }
}

Logging and diagnostics

You can enable file logging by providing an environment variable in the MCP config. The example below shows how to write logs to a file.

{
  "mcpServers": {
    "maxential-thinking": {
      "command": "node",
      "args": ["/path/to/dist/src/index.js"],
      "env": {
        "MAXENTIAL_LOG_FILE": "/path/to/error.log"
      }
    }
  }
}

Available tools

think

Add a thought to your reasoning chain

revise

Revise a previous thought in the chain

complete

Mark the current thinking chain as complete with a conclusion

branch

Create a new reasoning branch (like git) for alternative paths

switch_branch

Switch between branches; use main to return to the primary thread

list_branches

List all branches with their status

get_branch

Retrieve details for a specific branch

close_branch

Close a branch with an optional conclusion

merge_branch

Merge insights from a branch back to the main thread

get_thought

Retrieve a specific thought by its number in the chain

get_history

Get thought history, with optional filtering

reset

Clear the current session and start fresh

tag

Add semantic tags to thoughts (e.g., hypothesis, evidence, decision)

search

Find thoughts by content or tags

export

Export the entire thinking chain to Markdown or JSON

visualize

Generate ASCII or Mermaid diagrams of your thinking