
MCP Sequential Thinking Tools
Okay, I understand. I will act as a helpful assistant that guides problem-solving by: 1. **Breaking down complex problems into manageable steps.** I will identify the key stages involved in solving the problem. 2. **Recommending appropriate MCP (Meta-Cognitive Prompting) tools for each stage.** I will suggest specific techniques or prompts that can be used to facilitate thinking and problem-solving at each step. 3. **Providing confidence scores for each tool suggestion.** This will indicate how confident I am that the tool is a good fit for the stage. 4. **Offering rationales for my tool suggestions.** I will explain why I believe the suggested tool is helpful and how it can be applied. Let's get started! Please provide me with the complex problem you want to solve. I'm ready to help you break it down and find the right tools for the job. --- **Example of how I will respond (once you provide a problem):** **Problem:** (Let's say you provide: "How can I improve my team's communication?") **My Response:** Okay, improving team communication is a complex problem. Here's a breakdown into steps and suggested MCP tools: **Step 1: Identify Communication Bottlenecks and Pain Points** * **Goal:** Understand the current state of communication within the team and pinpoint specific areas that need improvement. * **Suggested MCP Tool:** **"5 Whys" Analysis** * **Confidence Score:** 90% * **Rationale:** The "5 Whys" technique helps to drill down to the root causes of communication problems. By repeatedly asking "Why?" about observed issues, you can uncover underlying factors that contribute to poor communication. For example, "Why is information not being shared effectively?" -> "Why are team members not attending meetings?" -> "Why are meetings perceived as unproductive?" etc. * **Suggested MCP Tool:** **"Brainstorming (with constraints)"** * **Confidence Score:** 80% * **Rationale:** Brainstorming can generate a wide range of potential problems and solutions. Adding constraints (e.g., "What are the biggest communication challenges given our current tools?") can focus the brainstorming session and make it more productive. **Step 2: Define Clear Communication Goals and Objectives** * **Goal:** Establish specific, measurable, achievable, relevant, and time-bound (SMART) goals for improving team communication. * **Suggested MCP Tool:** **"SMART Goal Setting"** * **Confidence Score:** 95% * **Rationale:** This is a direct application of the SMART framework. It ensures that the goals are well-defined and actionable. For example, "Increase team meeting attendance by 20% within the next quarter." * **Suggested MCP Tool:** **"Backward Planning"** * **Confidence Score:** 75% * **Rationale:** Starting with the desired outcome (improved communication) and working backward to identify the necessary steps can help create a clear roadmap. **Step 3: Generate Potential Solutions and Strategies** * **Goal:** Explore different approaches to address the identified communication bottlenecks and achieve the defined goals. * **Suggested MCP Tool:** **"SCAMPER"** * **Confidence Score:** 85% * **Rationale:** SCAMPER (Substitute, Combine, Adapt, Modify/Magnify/Minimize, Put to other uses, Eliminate, Reverse) is a creativity technique that can help generate novel solutions by prompting you to think about different ways to modify existing communication practices or tools. * **Suggested MCP Tool:** **"Analogical Thinking"** * **Confidence Score:** 70% * **Rationale:** Consider how other teams or organizations have successfully improved communication. What strategies did they use? Can those strategies be adapted to your team's context? **Step 4: Evaluate and Prioritize Solutions** * **Goal:** Assess the feasibility, impact, and cost of each potential solution and prioritize those that are most likely to be effective. * **Suggested MCP Tool:** **"Impact/Effort Matrix"** * **Confidence Score:** 90% * **Rationale:** This matrix helps to visually represent the potential impact of each solution against the effort required to implement it. This allows you to focus on high-impact, low-effort solutions first. * **Suggested MCP Tool:** **"Cost-Benefit Analysis"** * **Confidence Score:** 80% * **Rationale:** A more formal analysis of the costs and benefits of each solution can provide a more objective basis for prioritization. **Step 5: Implement and Monitor Progress** * **Goal:** Put the chosen solutions into action and track progress towards the defined goals. * **Suggested MCP Tool:** **"Action Planning"** * **Confidence Score:** 95% * **Rationale:** Create a detailed action plan that outlines who is responsible for each task, what the timeline is, and what resources are needed. * **Suggested MCP Tool:** **"Regular Check-ins and Feedback"** * **Confidence Score:** 90% * **Rationale:** Regularly monitor progress and solicit feedback from team members to identify any issues and make adjustments as needed. **Step 6: Reflect and Iterate** * **Goal:** Evaluate the effectiveness of the implemented solutions and identify areas for further improvement. * **Suggested MCP Tool:** **"After-Action Review (AAR)"** * **Confidence Score:** 90% * **Rationale:** An AAR is a structured process for reflecting on what happened, what went well, what could have been done better, and what lessons were learned. * **Suggested MCP Tool:** **"Continuous Improvement Cycle (PDCA)"** * **Confidence Score:** 85% * **Rationale:** The Plan-Do-Check-Act cycle provides a framework for continuous improvement by systematically planning, implementing, monitoring, and adjusting solutions. --- Now, please provide me with the problem you want to solve, and I'll apply this approach to it.
Tools
sequentialthinking_tools
A detailed tool for dynamic and reflective problem-solving through thoughts. This tool helps analyze problems through a flexible thinking process that can adapt and evolve. Each thought can build on, question, or revise previous insights as understanding deepens. IMPORTANT: When initializing this tool, you must pass all available tools that you want the sequential thinking process to be able to use. The tool will analyze these tools and provide recommendations for their use. When to use this tool: - Breaking down complex problems into steps - Planning and design with room for revision - Analysis that might need course correction - Problems where the full scope might not be clear initially - Problems that require a multi-step solution - Tasks that need to maintain context over multiple steps - Situations where irrelevant information needs to be filtered out - When you need guidance on which tools to use and in what order Key features: - You can adjust total_thoughts up or down as you progress - You can question or revise previous thoughts - You can add more thoughts even after reaching what seemed like the end - You can express uncertainty and explore alternative approaches - Not every thought needs to build linearly - you can branch or backtrack - Generates a solution hypothesis - Verifies the hypothesis based on the Chain of Thought steps - Recommends appropriate tools for each step - Provides rationale for tool recommendations - Suggests tool execution order and parameters - Tracks previous recommendations and remaining steps Parameters explained: - thought: Your current thinking step, which can include: * Regular analytical steps * Revisions of previous thoughts * Questions about previous decisions * Realizations about needing more analysis * Changes in approach * Hypothesis generation * Hypothesis verification * Tool recommendations and rationale - next_thought_needed: True if you need more thinking, even if at what seemed like the end - thought_number: Current number in sequence (can go beyond initial total if needed) - total_thoughts: Current estimate of thoughts needed (can be adjusted up/down) - is_revision: A boolean indicating if this thought revises previous thinking - revises_thought: If is_revision is true, which thought number is being reconsidered - branch_from_thought: If branching, which thought number is the branching point - branch_id: Identifier for the current branch (if any) - needs_more_thoughts: If reaching end but realizing more thoughts needed - current_step: Current step recommendation, including: * step_description: What needs to be done * recommended_tools: Tools recommended for this step * expected_outcome: What to expect from this step * next_step_conditions: Conditions to consider for the next step - previous_steps: Steps already recommended - remaining_steps: High-level descriptions of upcoming steps You should: 1. Start with an initial estimate of needed thoughts, but be ready to adjust 2. Feel free to question or revise previous thoughts 3. Don't hesitate to add more thoughts if needed, even at the "end" 4. Express uncertainty when present 5. Mark thoughts that revise previous thinking or branch into new paths 6. Ignore information that is irrelevant to the current step 7. Generate a solution hypothesis when appropriate 8. Verify the hypothesis based on the Chain of Thought steps 9. Consider available tools that could help with the current step 10. Provide clear rationale for tool recommendations 11. Suggest specific tool parameters when appropriate 12. Consider alternative tools for each step 13. Track progress through the recommended steps 14. Provide a single, ideally correct answer as the final output 15. Only set next_thought_needed to false when truly done and a satisfactory answer is reached
README
mcp-sequentialthinking-tools
这是对 MCP Sequential Thinking Server 的改编,旨在指导问题解决中的工具使用。该服务器帮助将复杂问题分解为可管理的步骤,并为每个阶段提供最有效的 MCP 工具的建议。
<a href="https://glama.ai/mcp/servers/zl990kfusy"> <img width="380" height="200" src="https://glama.ai/mcp/servers/zl990kfusy/badge" /> </a>
一个模型上下文协议 (MCP) 服务器,它将顺序思维与智能工具建议相结合。对于问题解决过程中的每个步骤,它都会提供工具使用建议,并附有置信度评分以及每个工具适用原因的理由。
特性
- 🤔 通过顺序思考进行动态和反思性的问题解决
- 🔄 灵活的思维过程,可以适应和发展
- 🌳 支持思考的分支和修订
- 🛠️ 为每个步骤提供智能工具推荐
- 📊 工具建议的置信度评分
- 🔍 工具推荐的详细理由
- 📝 步骤跟踪,包含预期结果
- 🔄 进度监控,包含先前和剩余步骤
- 🎯 每个步骤的替代工具建议
工作原理
该服务器分析您思考过程的每个步骤,并推荐适当的 MCP 工具来帮助完成任务。每个建议包括:
- 一个置信度评分(0-1),表明该工具与当前需求的匹配程度
- 一个清晰的理由,解释为什么该工具会有帮助
- 一个优先级,用于建议工具的执行顺序
- 可以使用的替代工具
该服务器与您环境中可用的任何 MCP 工具配合使用。它根据当前步骤的要求提供建议,但实际的工具执行由消费者(如 Claude)处理。
使用示例
以下是服务器如何指导工具使用的示例:
{
"thought": "初步研究步骤,了解 Svelte 5 中通用反应性的含义",
"current_step": {
"step_description": "收集有关 Svelte 5 通用反应性的初步信息",
"expected_outcome": "清楚理解通用反应性概念",
"recommended_tools": [
{
"tool_name": "search_docs",
"confidence": 0.9,
"rationale": "搜索 Svelte 文档以获取官方信息",
"priority": 1
},
{
"tool_name": "tavily_search",
"confidence": 0.8,
"rationale": "从可靠来源获取更多上下文",
"priority": 2
}
],
"next_step_conditions": [
"验证信息准确性",
"查找实现细节"
]
},
"thought_number": 1,
"total_thoughts": 5,
"next_thought_needed": true
}
该服务器跟踪您的进度并支持:
- 创建分支以探索不同的方法
- 使用新信息修改先前的想法
- 跨多个步骤维护上下文
- 根据当前发现建议后续步骤
配置
此服务器需要通过您的 MCP 客户端进行配置。以下是不同环境的示例:
Cline 配置
将其添加到您的 Cline MCP 设置中:
{
"mcpServers": {
"mcp-sequentialthinking-tools": {
"command": "npx",
"args": ["-y", "mcp-sequentialthinking-tools"]
}
}
}
带有 WSL 配置的 Claude Desktop
对于 WSL 环境,将其添加到您的 Claude Desktop 配置中:
{
"mcpServers": {
"mcp-sequentialthinking-tools": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"source ~/.nvm/nvm.sh && /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-sequentialthinking-tools"
]
}
}
}
API
该服务器实现了一个具有可配置参数的 MCP 工具:
sequentialthinking_tools
一种通过思考进行动态和反思性问题解决的工具,具有智能工具推荐。
参数:
thought
(string, required): 您当前的思考步骤next_thought_needed
(boolean, required): 是否需要另一个思考步骤thought_number
(integer, required): 当前思考编号total_thoughts
(integer, required): 估计需要的总思考次数is_revision
(boolean, optional): 这是否修改了先前的思考revises_thought
(integer, optional): 正在重新考虑哪个思考branch_from_thought
(integer, optional): 分支点思考编号branch_id
(string, optional): 分支标识符needs_more_thoughts
(boolean, optional): 是否需要更多思考current_step
(object, optional): 当前步骤建议,包含:step_description
: 需要做什么recommended_tools
: 包含置信度评分的工具推荐数组expected_outcome
: 对此步骤的期望next_step_conditions
: 下一步的条件
previous_steps
(array, optional): 已经推荐的步骤remaining_steps
(array, optional): 即将到来的步骤的高级描述
开发
设置
- 克隆存储库
- 安装依赖项:
pnpm install
- 构建项目:
pnpm build
- 在开发模式下运行:
pnpm dev
发布
该项目使用 changesets 进行版本管理。要发布:
- 创建一个 changeset:
pnpm changeset
- 对软件包进行版本控制:
pnpm changeset version
- 发布到 npm:
pnpm release
贡献
欢迎贡献!请随时提交 Pull Request。
许可证
MIT 许可证 - 有关详细信息,请参见 LICENSE 文件。
致谢
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。