"Tianji" — Thinking Models MCP Server

> Toolbox for intelligent thinking: Integrating systematic thinking methods into your problem-solving process

Table of Contents

- What is "Tianji"?
- Core Features
- Tools Overview
- Exploration Tools
- Problem-Solving Tools
- Creation Tools
- System and Learning Tools
- Tool Function Parameters and Return Values
- Exploration Tools
- Problem-Solving Tools
- Creation Tools
- System and Learning Tools
- Use Cases
- Quick Start
- Configuration Guide
- Developer Documentation
- Development Environment Setup
- Code Architecture
- API Documentation
- Extension Guidelines
- Testing
- Build and Deployment
- Coding Standards
- Common Development Issues and Troubleshooting
- License

What is "Tianji"?

"Tianji" is a powerful thinking model MCP server that integrates hundreds of thinking models, frameworks, and methodologies to help users think more systematically and comprehensively about problems. Through the MCP (Model Context Protocol) interface, AI assistants can access these thinking tools and seamlessly apply structured thinking methods to conversations. The name "Tianji" originates from the ancient Chinese saying "Heaven's secrets must not be revealed," implying that it helps users uncover deeper patterns of thinking and wisdom.

Core Features

- Rich Library of Thinking Models: Contains classic thinking models across multiple domains including decision theory, systems thinking, and probabilistic thinking
- Intelligent Model Recommendations: Automatically recommends the most suitable thinking models based on problem characteristics
- Interactive Reasoning Process: Guides users through structured thinking, analyzing problems step by step
- Learning and Adaptation System: Continuously improves recommendation algorithms through user feedback
- Model Creation and Combination: Allows creation of new models or combination of existing models to generate innovative thinking frameworks

Tools Overview

Exploration Tools

- list-models: List all thinking models or filter by category
- search-models: Search thinking models by keywords
- get-categories: Get all thinking model categories
- get-model-info: Get detailed information about a thinking model
- get-related-models: Get other models related to a specific model

Problem-Solving Tools

- recommend-models-for-problem: Recommend suitable thinking models based on problem keywords
- interactive-reasoning: Interactive reasoning process guidance
- generate-validate-hypotheses: Generate multiple hypotheses for a problem and provide validation methods
- explain-reasoning-process: Explain the reasoning process of a model and the thinking patterns applied

Creation Tools

- create-thinking-model: Create a new thinking model
- update-thinking-model: Update any field of an existing thinking model, including basic information and visualization data, without recreating the entire model
- emergent-model-design: Create new thinking models by combining existing ones
- delete-thinking-model: Delete unwanted thinking models

System and Learning Tools

- get-started-guide: Beginner's guide
- get-server-version: Get server version information
- count-models: Count the total number of current thinking models
- record-user-feedback: Record user feedback on thinking model experiences
- detect-knowledge-gap: Detect knowledge gaps in user queries
- get-model-usage-stats: Get usage statistics for thinking models
- analyze-learning-system: Analyze the status of the thinking model learning system

Tool Function Parameters and Return Values

Below are the detailed parameters and return values for all tool functions:

Exploration Tools

list-models

Lists all thinking models or filters by category.

Parameters:
- lang (required, default "zh"): Language code, options: ["zh", "en"]
- category (optional): Main category name
- subcategory (optional): Subcategory name (requires main category to be provided)
- limit (optional, default 100): Limit on the number of results returned

Return Value:

{

  "models": [

    {

      "id": "modelID",

      "name": "model name",

      "definition": "model definition",

      "category": "model category"

    }

    // ... more models

  ],

  "total": total number of models queried,

  "filter": "applied filter conditions"

}

search-models

Search thinking models by keywords.

Parameters:
- query (required): Search keywords
- lang (required, default "zh"): Language code, options: ["zh", "en"]
- limit (optional, default 10): Limit on the number of results returned

Return Value:

{

  "results": [

    {

      "id": "modelID",

      "name": "model name",

      "definition": "model definition",

      "purpose": "model purpose",

      "match_score": match score,

      "match_reasons": ["match reason 1", "match reason 2"]

    }

    // ... more matching results

  ],

  "total": total number of matching models,

  "query": "search keywords"

}

get-categories

Get all thinking model categories.

Parameters:
- lang (required, default "zh"): Language code, options: ["zh", "en"]

Return Value:

{

  "categories": [

    {

      "name": "category name",

      "count": number of models in this category,

      "subcategories": [

        {

          "name": "subcategory name",

          "count": number of models in this subcategory

        }

        // ... more subcategories

      ]

    }

    // ... more categories

  ],

  "total_categories": total number of categories,

  "total_models": total number of all models

}

get-model-info

Get detailed information about a thinking model.

Parameters:
- model_id (required): Unique ID of the thinking model
- fields (optional, default ["basic"]): Fields to return, options: ["all", "basic", "detail", "teaching", "warnings", "visualizations"]
- lang (required, default "zh"): Language code, options: ["zh", "en"]

…