Deep Thinker

Name: Deep Thinker
Author: hubinoretros

@hubinoretros

About Deep Thinker

Advanced cognitive thinking MCP server with DAG-based thought graph, multiple reasoning strategies, metacognition, and self-evaluation.

#mcp-server #thinking-tool #reasoning-engine #cognitive-engine

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "deep-thinker": {
      "command": "npx",
      "args": [
        "-y",
        "deep-thinker"
      ]
    }
  }
}

Tools

Add a thought to the cognitive graph using the current strategy. Supports sequential, dialectic, parallel, analogical, and abductive reasoning strategies. Each thought becomes a node in a DAG with confidence scoring, edges, and metadata.

Evaluate the thinking process: score confidence, generate critiques, and assess overall graph health. Provides detailed analysis of weak spots and strong reasoning paths.

Metacognitive operations: view the current thinking state, get strategy suggestions, switch strategies, and receive guidance on improving reasoning. The system automatically detects stuck states and recommends actions.

Query and visualize the thought graph. View the DAG structure, find paths, inspect branches, and get statistics.

Prune and optimize the thought graph. Remove dead ends, consolidate redundant branches, and optimize reasoning paths. Helps maintain graph efficiency during deep reasoning.

Reset the thought graph and metacognitive state. Start a fresh reasoning session.

Overview

What is Deep Thinker?

Deep Thinker is an advanced cognitive MCP server with DAG-based thought graphs, multiple reasoning strategies, metacognition, and self-evaluation. It extends sequential thinking by supporting branching, merging, and cross-edges.

How to use Deep Thinker?

—

Key features of Deep Thinker

DAG-based thought graph with branching, merging, and cross-edges
Five reasoning strategies: Sequential, Dialectic, Parallel, Analogical, Abductive
Multi-factor confidence scoring with support/contradiction analysis
Automatic self-critique with severity levels and confidence adjustments
Metacognitive engine detecting stuck states and stagnant reasoning
Knowledge integration for attaching, gap detection, and consistency validation
Thought pruning: dead-end detection, redundancy removal, branch elimination

Use cases of Deep Thinker

Complex problem solving that requires structured deep reasoning
Scenarios needing dialectical or abductive inference for best explanations
Tasks where self-evaluation and confidence calibration are critical
Exploratory analysis with branching and merging of multiple reasoning paths
Knowledge-intensive reasoning requiring external knowledge integration and validation

FAQ from Deep Thinker

What reasoning strategies does Deep Thinker support?

Deep Thinker supports Sequential, Dialectic (thesis→antithesis→synthesis), Parallel, Analogical, and Abductive (inference to best explanation) strategies.

How does the metacognitive engine work?

The metacognitive engine detects stuck states, stagnation, and declining confidence, then suggests strategy switches and corrective actions.

What is thought pruning and why is it needed?

Thought pruning removes dead-ends, redundant thoughts, and deep unproductive branches to optimize the reasoning graph.

How is confidence scoring calculated?

Confidence scoring uses multi-factor evaluation including support/contradiction analysis, depth penalties, and knowledge integration boosts.

How does Deep Thinker differ from sequential-thinking MCP?

Deep Thinker uses a DAG-based thought graph with branching, merging, and cross-edges rather than a linear chain, and adds multiple reasoning strategies, confidence scoring, self-critique, metacognition, knowledge integration, and pruning.

Comments

More Other MCP servers

Inbox Zero AI MCP

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

Inbox Zero AI

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K