Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@divergent-thinking-mcp Brainstorm innovative ideas for remote team collaboration tools."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that promotes divergent and creative thinking patterns for creation - the Supplement of sequential logical thinking. 一个MCP（模型上下文协议）服务器，促进创造性思维模式，是顺序逻辑思维的补充。
Designed to provide creative inspiration for both humans and AI agents, complementing the structured nature of sequential thinking. 旨在为人类与AI智能体提供创意与灵感，作为对传统顺序性思维的补充。
Related MCP server: COAIA Sequential Thinking
This MCP server provides a single comprehensive tool that offers 6 powerful creativity methods through one unified interface, aiming to reduce confusion and cognitive overload. 此MCP服务器提供单一综合工具，通过统一界面提供6种强大的创意方法，旨在减轻混乱和认知负担。
divergent_thinking - Comprehensive Creative Thinking Tool / 综合创意思维工具A unified tool providing access to 6 proven creativity methodologies through parameter-driven functionality selection: 通过参数驱动功能选择提供6种经过验证的创意方法的统一工具：
Available Thinking Methods / 可用思维方法：
structured_process (Default/默认) - Multi-turn comprehensive exploration with thought tracking and branching
多轮综合探索，具有思维跟踪和分支功能
generate_branches - Create 3 different creative directions from a single thought (single response)
从单一想法创建3个不同的创意方向（单次响应）
perspective_shift - View thoughts through unusual viewpoints (inanimate objects, abstract concepts, impossible beings)
通过不寻常的视角查看想法（无生命物体、抽象概念、不可能的存在）
creative_constraint - Apply strategic limitations to force breakthrough innovation
应用战略限制来强制突破性创新
combine_thoughts - Merge two concepts into novel hybrid solutions
将两个概念合并为新颖的混合解决方案
reverse_brainstorming - Explore failure modes to discover breakthrough solutions
探索失败模式以发现突破性解决方案
Key Features / 主要特性：
🧠 Domain-Aware Intelligence: Intelligent word selection and context-sensitive creativity replacing generic random outputs 领域感知智能：智能词汇选择和上下文敏感创造力，取代通用随机输出
📊 Contextual Creativity Methods: Enhanced SCAMPER, analogical thinking, biomimicry, and Six Thinking Hats with domain-specific intelligence 上下文创意方法：增强的SCAMPER、类比思维、仿生学和六顶思考帽，具有领域特定智能
🎨 Interactive Context Specification: Agent-driven domain, audience, time period, resources, and goals specification for targeted creativity 交互式上下文规范：代理驱动的领域、受众、时间段、资源和目标规范，实现有针对性的创造力
🔍 Multi-word Domain Precision: 78+ specific domains like "mobile app development", "healthcare technology", "sustainable agriculture" 多词领域精度：78+个特定领域，如"移动应用开发"、"医疗技术"、"可持续农业"
🔄 Multi-turn vs Single-shot: structured_process provides complete multi-turn exploration; others are single-response methods
多轮与单次：structured_process提供完整的多轮探索；其他为单次响应方法
⚡ Intelligent Routing: Single tool interface with method-specific parameter handling and domain-aware processing 智能路由：具有方法特定参数处理和领域感知处理的单一工具界面
🎲 Deterministic Results: Optional seed parameter for reproducible creative outputs 确定性结果：可选种子参数用于可重现的创意输出
Add to your MCP client configuration:(uv needed) 添加到您的MCP客户端配置：(需要uv)
{
"mcpServers": {
"divergent-thinking": {
"command": "uvx",
"args": ["divergent-thinking-mcp"],
}
}
}The MCP server provides intelligent, context-sensitive creativity with professional-grade outputs tailored to specific domains: MCP服务器提供智能的、上下文敏感的创造力，具有针对特定领域定制的专业级输出：
🎯 Transformation Examples:
Before: "How does 'butterfly' relate to secure systems?" (generic random)
After: "How does 'encryption' relate to secure systems in cybersecurity applications?" (domain-aware)
💡 Professional Relevance:
AI Domain: Uses terms like "neural networks", "machine learning", "optimization" instead of random words
Healthcare: Focuses on "patient safety", "clinical evidence", "regulatory compliance"
Business: Emphasizes "market positioning", "competitive advantage", "ROI optimization"
{
"thought": "Create an innovative learning platform",
"thinking_method": "structured_process",
"domain": "educational technology",
"target_audience": "remote students",
"time_period": "2025-2030",
"resources": "cloud computing, mobile devices, limited budget",
"goals": "improve engagement, reduce costs, increase accessibility"
}🎯 Domain-Aware Output Example:
SCAMPER Enhancement: "How could 'adaptive learning' substitute traditional methods in educational technology applications?"
Analogical Thinking: "How is your learning platform like 'cognitive science learning theories' in educational contexts?"
Biomimicry: "How could your platform mimic 'neural plasticity' for personalized learning adaptation?"
{
"thought": "Design a smart home security system",
"thinking_method": "generate_branches",
"domain": "cybersecurity",
"target_audience": "elderly users",
"goals": "ease of use, reliability, affordability"
}🔒 Cybersecurity-Aware Outputs:
Domain Terms: Uses "authentication", "encryption", "threat detection" instead of random words
Six Thinking Hats: "What threat vectors does this address?" (White Hat - Facts)
Professional Context: "How could this improve overall security posture for elderly users?"
{
"thought": "Develop a food delivery service",
"thinking_method": "creative_constraint",
"domain": "e-commerce",
"constraint": "must work without smartphones",
"target_audience": "rural communities",
"resources": "limited internet, local partnerships"
}{
"thought": "Reimagine public transportation",
"thinking_method": "perspective_shift",
"domain": "urban transportation",
"time_period": "2050",
"perspective_type": "impossible_being",
"goals": "zero emissions, universal accessibility"
}Quantitative Improvements / 量化改进:
Domain Relevance: 30% → 90%+ (relevant terms in creative outputs)
Context Sensitivity: Generic → Domain-specific patterns
All creativity techniques now feature domain-aware intelligence:
🎨 SCAMPER Method: Domain-specific prompts using intelligent word selection
Before: "What if we substitute the main component with something unexpected?"
After: "What if you replaced key components with 'neural networks' for AI applications?"
🔗 Analogical Thinking: Domain-relevant analogies from biological, mathematical, and engineering systems
Before: Generic nature analogies
After: "How is your AI system like 'immune system pattern recognition' in biological contexts?"
🌿 Biomimicry: Nature-inspired solutions tailored to specific domains
Before: Random nature examples
After: "How could your renewable energy system mimic 'photosynthesis energy conversion'?"
🎭 Six Thinking Hats: Professional domain-specific perspectives
Before: Generic emotional/logical prompts
After: "What clinical evidence supports this healthcare technology approach?" (White Hat)
💭 Word Association: Domain-relevant word selection replacing random combinations
Before: "butterfly" + "cybersecurity"
After: "encryption" + "network security"
Choose from 78+ specific multi-word domains: 从78+个特定的多词领域中选择：
Design & UX: product design, user interface design, user experience design
Technology: software development, mobile app development, artificial intelligence, cybersecurity
Business: business strategy, digital marketing, e-commerce, startup ventures
Healthcare: medical devices, healthcare technology, telemedicine, patient care
Education: educational technology, online learning, curriculum development
Environment: renewable energy, sustainable agriculture, green technology
Transportation: urban transportation, electric vehicles, autonomous vehicles
And many more... / 还有更多...
A comprehensive tool for generating creative thoughts and breakthrough ideas through structured divergent thinking processes with interactive context specification.
This unified tool provides access to 6 powerful creativity methods through a single interface. It offers both comprehensive multi-turn exploration (structured_process) and quick single-shot creative techniques, with agent-driven context specification for more targeted and relevant creative outputs.
Primary use: Complex creative challenges requiring systematic exploration (use structured_process)
Quick tasks: Need rapid creative input or specific creative techniques (use single-shot methods)
Problem solving: Breaking through mental blocks and conventional thinking patterns
Innovation: Developing breakthrough solutions and novel concepts
Ideation: Generating multiple creative directions and alternatives
Context-specific creativity: When you need creativity tailored to specific domains, audiences, or constraints
Required domain specification: Ensures targeted, relevant creativity by requiring explicit domain selection from 78+ multi-word options
Multi-turn structured exploration: Complete guided creative journey with thought tracking and branching (structured_process - 多轮且结构完整的思考模式)
Single-shot quick methods: Rapid creative techniques for specific needs (单次响应方法)
Interactive context specification: Agent-driven domain, audience, time period, resources, and goals specification for precise targeting
Advanced creativity algorithms: SCAMPER, Six Thinking Hats, morphological analysis, reverse brainstorming with context awareness
Intelligent parameter routing: Single tool interface with method-specific parameter handling and comprehensive validation
Comprehensive coverage: 6 proven creativity methodologies in one unified interface
Adaptive depth: Adjusts exploration complexity based on problem requirements and context richness
Required:
thought: Your primary idea, problem, or concept to work with (1-5000 characters)
thinking_method: Which creativity technique to apply (default: structured_process)
structured_process: Multi-turn comprehensive exploration (RECOMMENDED DEFAULT)
generate_branches: Create 3 different creative directions (single response)
perspective_shift: View through unusual viewpoints (single response)
creative_constraint: Apply strategic limitations (single response)
combine_thoughts: Merge two concepts (single response)
reverse_brainstorming: Explore failure modes (single response)
domain: REQUIRED - Specific field/domain for targeted creativity (must be explicitly specified)
Examples: "product design", "mobile app development", "healthcare technology", "sustainable agriculture", "e-commerce", "artificial intelligence", etc.
Choose from 78+ available multi-word domain options for precise context
Interactive Context (Optional):
target_audience: Who the solution is for (e.g., 'students', 'professionals', 'elderly')
time_period: Time context (e.g., 'current', 'future', '2030s', 'historical')
resources: Available resources/constraints (comma-separated)
goals: Specific objectives (comma-separated)
Method-Specific:
thought2: Second concept for combination (required only for combine_thoughts)
constraint: Creative limitation to apply (for creative_constraint, default: "introduce an impossible element")
perspective_type: Viewpoint to adopt (for perspective_shift: inanimate_object, abstract_concept, impossible_being)
Structured Process Options:
thoughtNumber: Position in thinking sequence (default: 1)
totalThoughts: Expected total thoughts (default: 3)
nextThoughtNeeded: Continue sequence (default: true)
generate_branches: Create multiple paths (default: false)
Enhancement Options:
use_advanced_techniques: Enable SCAMPER, Six Thinking Hats, etc. (default: false)
seed: Random seed for consistent results (1-999999)
Always specify a domain - This is now required for targeted, relevant creativity output
Choose the most specific domain that matches your challenge (e.g., "mobile app development" not "software development")
Use multi-word domains for precision (e.g., "healthcare technology", "sustainable agriculture")
Start with structured_process for most creative challenges - it provides the complete multi-turn thinking experience
Use single-shot methods only when you need quick, specific creative input rather than comprehensive exploration
Provide clear, specific thoughts as input - the more detailed your thought, the better the creative output
Enhance with context parameters for even more targeted creativity:
Define target_audience for user-centered creative solutions
Specify time_period for temporally-aware creativity
List resources and goals for constraint-aware innovation
Choose appropriate thinking_method based on your specific creative need:
Complex problems → structured_process
Quick brainstorming → generate_branches
Stuck in conventional thinking → perspective_shift
Need breakthrough innovation → creative_constraint
Have multiple ideas to merge → combine_thoughts
Standard methods not working → reverse_brainstorming
Enable use_advanced_techniques for more sophisticated creativity algorithms when dealing with complex challenges
Use seed parameter when you need consistent, reproducible creative outputs across multiple runs
Iterate thoughtfully - let each creative output inform your next exploration direction
Be specific with context - the more precise your domain and context parameters, the more targeted and useful the creative output
Examples:
{'description': 'Complete structured creative exploration (RECOMMENDED DEFAULT)', 'parameters': {'thought': 'Develop sustainable transportation solution', 'thinking_method': 'structured_process', 'domain': 'urban transportation', 'use_advanced_techniques': True}}
{'description': 'Agent-driven context specification for targeted creativity', 'parameters': {'thought': 'Create an innovative learning platform', 'thinking_method': 'structured_process', 'domain': 'educational technology', 'target_audience': 'remote students', 'time_period': '2025-2030', 'resources': 'cloud computing, mobile devices, limited budget', 'goals': 'improve engagement, reduce costs, increase accessibility'}}
{'description': 'Domain-specific creative branching', 'parameters': {'thought': 'Design a smart home security system', 'thinking_method': 'generate_branches', 'domain': 'cybersecurity', 'target_audience': 'elderly users', 'goals': 'ease of use, reliability, affordability'}}
{'description': 'Context-aware creative constraints', 'parameters': {'thought': 'Develop a food delivery service', 'thinking_method': 'creative_constraint', 'domain': 'e-commerce', 'constraint': 'must work without smartphones', 'target_audience': 'rural communities', 'resources': 'limited internet, local partnerships'}}
{'description': 'Time-specific perspective shifting', 'parameters': {'thought': 'Reimagine public transportation', 'thinking_method': 'perspective_shift', 'domain': 'urban transportation', 'time_period': '2050', 'perspective_type': 'impossible_being', 'goals': 'zero emissions, universal accessibility'}}
{'description': 'Minimal required parameters', 'parameters': {'thought': 'Create a new type of office chair', 'thinking_method': 'generate_branches', 'domain': 'product design'}}
{'description': 'Domain-focused constraint creativity with minimal context', 'parameters': {'thought': 'Design eco-friendly packaging', 'thinking_method': 'creative_constraint', 'domain': 'sustainable agriculture', 'constraint': 'must be made from recycled materials'}}
| Name | Required | Description | Default |
|---|---|---|---|
| thought | Yes | The primary thought, idea, or concept to work with | |
| thinking_method | Yes | The divergent thinking method to apply. Choose 'structured_process' for comprehensive multi-turn exploration, or single-shot methods for quick creative input. | structured_process |
| thought2 | No | Second thought for combination method (required only for combine_thoughts) | |
| constraint | No | Creative limitation to apply (for creative_constraint method) | introduce an impossible element |
| perspective_type | No | Viewpoint to adopt (for perspective_shift method) | inanimate_object |
| use_advanced_techniques | No | Enable advanced creativity techniques (Six Thinking Hats, SCAMPER, etc.) | |
| seed | No | Random seed for deterministic results (optional) | |
| domain | Yes | REQUIRED: Specific domain/field for targeted creativity context. Must be explicitly specified by agent for precise, relevant creative outputs. | |
| target_audience | No | Optional: Target audience for user-centered creative solutions. Specify who will use/benefit from the solution (e.g., 'remote students', 'elderly users', 'small business owners', 'healthcare professionals') | |
| time_period | No | Optional: Time context for temporally-aware creativity. Specify when the solution will be implemented or relevant (e.g., 'current', '2030s', 'next decade', 'post-pandemic era') | |
| resources | No | Optional: Available resources and constraints for realistic innovation. Comma-separated list of what you have to work with (e.g., 'limited budget, cloud infrastructure, mobile devices, government grants') | |
| goals | No | Optional: Specific objectives and success criteria for goal-oriented creativity. Comma-separated list of what you want to achieve (e.g., 'reduce costs, improve user experience, increase accessibility, enhance security') | |
| thoughtNumber | No | Position of current thought in sequence (for structured_process) | |
| totalThoughts | No | Expected total thoughts in sequence (for structured_process) | |
| nextThoughtNeeded | No | Whether to continue the thinking sequence (for structured_process) | |
| generate_branches | No | Whether to create multiple divergent paths (for structured_process) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses that the tool uses structured processes, single-shot methods, and interactive context specification. It mentions parameter routing and validation. As a creativity tool, it is expected to be non-destructive, and the description aligns with that. However, it does not explicitly state side effects, rate limits, or authorization needs, but these are less relevant for such a tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections but is overly verbose. It contains redundancy, such as repeating parameter details in 'PARAMETERS EXPLAINED' and 'YOU SHOULD'. The 'KEY FEATURES' section overlaps with usage. While structured, it could be trimmed to half without losing essential information, achieving better conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (16 parameters, 6 methods, no output schema), the description is extremely comprehensive. It covers all parameters with explanations, provides usage guidance for each method, includes multiple examples, and addresses context parameters like domain, audience, time period, resources, and goals. It compensates for the lack of output schema by thoroughly describing the tool's behavior and intended use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant value beyond the schema. For example, it explains each thinking_method in detail, provides examples for domain (list of 78+ options), and gives context for method-specific parameters like thought2, constraint, and perspective_type. It includes a 'PARAMETERS EXPLAINED' section and usage examples, substantially enhancing parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'generating creative thoughts and breakthrough ideas through structured divergent thinking processes.' It distinguishes between 6 different methods, providing a specific verb (generate) and resource (creative thoughts/ideas). Since there are no sibling tools, differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a dedicated 'WHEN TO USE' section listing primary use cases and quick tasks. It provides guidance on choosing the appropriate thinking_method based on need (e.g., complex problems → structured_process, quick brainstorming → generate_branches). However, it does not explicitly state when not to use the tool or provide exclusions, only alternatives within the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusion between tools. The single tool's purpose is clearly defined, and all functionality is consolidated within it.
The lone tool name 'divergent_thinking' follows a consistent snake_case pattern, which is clear and predictable. No naming conflicts arise from having a single tool.
While the server's purpose is served by one comprehensive tool, the tool is heavily overloaded with multiple methods and parameters. Splitting into separate tools for each creativity method could improve modularity and clarity.
The tool covers a wide range of creativity techniques (SCAMPER, Six Thinking Hats, etc.) and allows context specification, making it fairly complete for divergent thinking. Minor gaps may exist, but overall it addresses the domain well.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
33 tools that make AI write, implement, and verify intent against explicit, testable constraints.
Provides UX capabilities to enhance the design output and understanding of AI systems.
Brand-aware creative studio for Claude: 200+ tools for on-brand ads, video, email and campaigns.
Dreamtap provides sources of inspiration to your AI to make it more creative.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Fridayxiao/divergent-thinking-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
