Think MCP Server

MCP Server for structured sequential thinking with Burst Thinking, Logic Methodology Generator, branching, revisions, dead-ends tracking, and fuzzy

Local serverstdioTypeScript

What is the Think MCP server?

MCP Server for structured sequential thinking with Burst Thinking, Logic Methodology Generator, branching, revisions, dead-ends tracking, and fuzzy recall. That is what the think mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Reason step by step, branch when needed, block weak finals, and keep useful memory across sessions.

  • They answer too early
  • They stay linear when the task needs alternatives or critique
  • They lose earlier insights between steps
  • They finish with confidence that is not backed by verification

Getting it running

Installation goes through your MCP client rather than a global install: point it at @gofman3/think-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • think — Add one structured reasoning step
  • think_batch — Submit one already-built reasoning chain
  • think_cycle — Adaptive reasoning state machine with a hard process gate
  • think_logic — Return a read-only analysis checklist
  • think_recall — Search the active scope or stored insights
  • think_done — Finalize a think or think_batch scope
  • think_reset — Clear the active scope state

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Think's toolset — think, think_batch, think_cycle and 4 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
thinkAdd one structured reasoning step
think_batchSubmit one already-built reasoning chain
think_cycleAdaptive reasoning state machine with a hard process gate
think_logicReturn a read-only analysis checklist
think_recallSearch the active scope or stored insights
think_doneFinalize a think or think_batch scope
think_resetClear the active scope state

How to install the Think MCP server

### MCP config

```json
{
  "mcpServers": {
    "think": {
      "command": "npx",
      "args": ["-y", "@gofman3/think-mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Think to think.
  • Use Think to think batch.
  • Use Think to think cycle.

Frequently asked questions

It connects Think to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (think, think_batch, think_cycle, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Think directly.