MAXential Thinking MCP

A structured, persistent reasoning workspace for AI. Provides 20 tools for building thought chains, exploring alternatives through branching, revising earlier thinking, searching reasoning history, and persisting sessions across context window resets and server restarts.

AI's built-in reasoning is ephemeral — when context windows fill, thinking gets compressed or lost. Complex problems need exploration of multiple approaches, backtracking when paths fail, and the ability to resume where you left off. MAXential externalizes reasoning into a workspace that persists, branches, and survives.

Origin

Forked from Anthropic's sequential-thinking MCP server, which provided a single tool with 9 parameters. Its schema included branching parameters (branch_from_thought, branch_id) but had no tools to create, switch, or manage branches — the parameters were effectively inert.

MAXential replaced that single tool entirely and built 20 purpose-specific tools across three releases:

Tools

Core Thinking

Branching

Navigation

Organization

Session Persistence

Sessions are automatically persisted to SQLite as you work. Every think, branch, tag, and revise call writes through to disk in real time. Sessions survive server restarts, context window resets, and new conversations — pick up where you left off.

What the original provides vs. what MAXential provides

Browsing session history

Session data is stored in a standard SQLite database at .maxential/thinking.db. There are several ways to browse past reasoning sessions:

Through the tools themselves — ask AI to use session_list to browse sessions, session_load to restore one, or session_summary for a compressed overview. AI can format, search, and summarize session content conversationally.

With a SQLite browser — open .maxential/thinking.db in any SQLite viewer (VS Code/VSCodium extensions, DB Browser for SQLite, or similar). The schema is straightforward:

From the terminal:

sqlite3 .maxential/thinking.db "SELECT name, status, datetime(created_at/1000, 'unixepoch', 'localtime') as created FROM sessions ORDER BY updated_at DESC LIMIT 10;"

Development

npm install          # Install dependencies
npm run build        # Build TypeScript
npm run watch        # Watch mode
npm test             # Run tests with coverage
npm run test:unit    # Unit tests only
npm run test:integration  # Integration tests only

Installation

Claude Desktop / Claude Code

Add to your MCP configuration:

Claude Desktop config location:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

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

From source

git clone https://github.com/BAM-DevCrew/MAXential-Thinking-MCP.git
cd MAXential-Thinking-MCP
npm install
npm run build

Then configure:

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

Configuration

Persistence

Session data is stored in SQLite. By default, the database is created at .maxential/thinking.db in the working directory.

{
  "mcpServers": {
    "maxential-thinking": {
      "command": "npx",
      "args": ["-y", "@bam-devcrew/maxential-thinking-mcp"],
      "env": {
        "MAXENTIAL_DB_PATH": "/path/to/your/thinking.db"
      }
    }
  }
}

If SQLite initialization fails (permissions, native module issues), the server falls back to in-memory mode automatically — it never crashes.

Add .maxential/ to your project's .gitignore to keep session data out of version control.

Logging

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

Usage

You don't call these tools directly — you ask your AI to use MAXential thinking, and it calls the tools as part of its reasoning. Here are examples of what that looks like in practice.

Working through a decision:

use maxential thinking for this - should we use REST or GraphQL for the new API?

AI builds a thought chain analyzing the question, branches to explore each approach separately, adds thoughts with tradeoffs, merges the findings, and reaches a conclusion. The entire reasoning process is numbered, structured, and persisted.

Exploring multiple approaches:

think through the auth redesign using maxential - I want to see branches for JWT, session tokens, and OAuth

AI creates three branches, reasons through each approach independently, then merges the insights back to compare. You can ask it to switch between branches, close dead ends, or dig deeper into a specific path.

Resuming previous thinking:

load up that session where you analyzed our database optimization options

AI browses saved sessions, finds the match, restores it with all thoughts, branches, and tags intact, and continues reasoning from where it left off — even across different conversations.

Reviewing past reasoning:

search your maxential thinking history for anything tagged as a decision

AI searches across the session's tagged thoughts and returns the results. You can also ask it to export the full chain as markdown, or generate a diagram of the thought structure.

Getting a quick summary:

give me a summary of that session - just the key findings, keep it short

AI generates a compressed summary of the session's conclusions, tagged highlights, and branch results — useful for loading context without replaying the full chain.

License

MIT