thinking_models_mcp

Thinking Models MCP Server

Tianji gives AI assistants access to thinking models for structured problem solving. Users can explore frameworks, get recommendations for a problem, work through reasoning stages, and create or revise models through MCP tools.

Server facts

thinking_models_mcp MCP Server

Project

License
Not specified

Tech

Runtime / language
html
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
31
Last commit
Data as of

Tags

  • model
  • thinking

Overview

Tianji organizes thinking frameworks around discovery and application, with material spanning decision theory, systems thinking, and probabilistic thinking. AI assistants can browse categories, filter model lists, search by keyword, and retrieve related frameworks. Model details can include application guidance, teaching explanations, limitations, common pitfalls, and visualization data. Language parameters support Chinese and English. For a specific problem, the recommendation tool accepts keywords and optional context, returning matching models with reasons for their relevance.

The reasoning workflow covers gathering information, forming hypotheses, testing them, and reaching a conclusion. Separate tools propose hypotheses with validation methods and potential biases, or explain supplied reasoning steps in relation to the models used. Users can also create models, revise existing content, and combine concepts from existing frameworks into new ones. Feedback recording, knowledge-gap detection, usage statistics, and learning-system analysis provide ways to examine model use and recommendation behavior. A beginner guide, model counter, and server-version tool round out the available interface.

thinking_models_mcp setup notes

  • thinking_models_mcp records stdio only; confirm a network transport upstream before planning remote access.
  • thinking_models_mcp has no recorded license; confirm reuse terms in its repository.

Related MCP servers