mcp-chain-of-thought
mcp-chain-of-thought
Tools
plan_task
Initialize and detail the task flow, establish clear goals and success criteria, optionally reference existing tasks for continuation planning
analyze_task
Deeply analyze task requirements and systematically check the codebase, evaluate technical feasibility and potential risks. If code is needed, use pseudocode format providing only high-level logic flow and key steps, avoiding complete code.
reflect_task
Critically review analysis results, evaluate solution completeness and identify optimization opportunities, ensuring the solution aligns with best practices. If code is needed, use pseudocode format providing only high-level logic flow and key steps, avoiding complete code.
split_tasks
Decompose complex tasks into independent subtasks, establishing dependencies and priorities. ## updateMode - **append**: Keep existing tasks and add new ones - **overwrite**: Delete unfinished tasks, keep completed ones - **selective**: Intelligently match and update existing tasks based on name - **clearAllTasks**: Clear all tasks and create a backup (preferred mode) ## Key Requirements - **Provide concise pseudocode**: Only provide high-level logic flow and key steps, avoid complete code - **Consolidate when necessary**: Simple modifications can be integrated with other tasks to avoid excessive task count - **Submit in batches**: If there are too many tasks, use the "split_tasks" tool with parameters not exceeding 5000 characters
list_tasks
Generate a structured task list, including complete status tracking, priority, and dependencies
execute_task
Execute a specific task according to the predefined plan, ensuring the output of each step meets quality standards
verify_task
Comprehensively verify task completion, ensuring all requirements and technical standards are met without missing details
complete_task
Formally mark a task as completed, generate a detailed completion report, and update the dependency status of related tasks
delete_task
Delete unfinished tasks, but does not allow deleting completed tasks, ensuring the integrity of system records
clear_all_tasks
Clear unfinished tasks and reset the task list
update_task
Update task content, including name, description and notes, dependent tasks, related files, implementation guide and verification criteria. Completed tasks only allow updating summary and related files
query_task
Search tasks by keyword or ID, displaying abbreviated task information
get_task_detail
Get the complete detailed information of a task based on its ID, including unabridged implementation guides and verification criteria, etc.
process_thought
Engage in a flexible and evolving thinking process by creating, questioning, validating, and refining ideas to progressively deepen understanding and generate effective solutions. When needing to gather data, analyze, or research, prioritize reviewing relevant project code; if such code doesn't exist, search the web rather than speculating. Set nextThoughtNeeded to false when thinking is sufficient, otherwise adjust total_thoughts to extend the process
init_project_rules
Initialize project rules. Call this tool when the user requests to generate or initialize the project specification file, or if the user requests to change or update the project specification.
README
MCP Chain of Thought
🚀 An intelligent task management system based on Model Context Protocol (MCP), providing an efficient programming workflow framework for AI Agents.
<a href="https://glama.ai/mcp/servers/@liorfranko/mcp-chain-of-thought"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@liorfranko/mcp-chain-of-thought/badge" /> </a>
📑 Table of Contents
- ✨ Features
- 🧭 Usage Guide
- 🔧 Installation
- 🔌 Using with MCP-Compatible Clients
- 🛠️ Tools Overview
- 🤖 Recommended Models
- 📄 License
- 📚 Documentation
✨ Features
- 🧠 Task Planning & Analysis: Deep understanding of complex task requirements
- 🧩 Intelligent Task Decomposition: Break down large tasks into manageable smaller tasks
- 🔄 Dependency Management & Status Tracking: Handle dependencies and monitor progress
- ✅ Task Verification: Ensure results meet requirements
- 💾 Task Memory: Store task history for reference and learning
- ⛓️ Thought Chain Process: Step-by-step reasoning for complex problems
- 📋 Project Rules: Define standards to maintain consistency
- 🌐 Web GUI: Optional web interface (enable with
ENABLE_GUI=true) - 📝 Detailed Mode: View conversation history (enable with
ENABLE_DETAILED_MODE=true)
🧭 Usage Guide
🚀 Quick Start
- 🔽 Installation: Install MCP Chain of Thought via Smithery or manually
- 🏁 Initial Setup: Tell the Agent "init project rules" to establish project-specific guidelines
- 📝 Plan Tasks: Use "plan task [description]" to create a development plan
- 👀 Review & Feedback: Provide feedback during the planning process
- ▶️ Execute Tasks: Use "execute task [name/ID]" to implement a specific task
- 🔄 Continuous Mode: Say "continuous mode" to process all tasks sequentially
🔍 Memory & Thinking Features
- 💾 Task Memory: Automatically saves execution history for reference
- 🔄 Thought Chain: Enables systematic reasoning through
process_thoughttool - 📋 Project Rules: Maintains consistency across your codebase
🔧 Installation
🔽 Via Smithery
npx -y @smithery/cli install @liorfranko/mcp-chain-of-thought --client claude
🔽 Manual Installation
npm install
npm run build
🔌 Using with MCP-Compatible Clients
⚙️ Configuration in Cursor IDE
Add to your Cursor configuration file (~/.cursor/mcp.json or project-specific .cursor/mcp.json):
{
"mcpServers": {
"chain-of-thought": {
"command": "npx",
"args": ["-y", "mcp-chain-of-thought"],
"env": {
"DATA_DIR": "/path/to/project/data", // Must use absolute path
"ENABLE_THOUGHT_CHAIN": "true",
"TEMPLATES_USE": "en",
"ENABLE_GUI": "true",
"ENABLE_DETAILED_MODE": "true"
}
}
}
}
⚠️ Important:
DATA_DIRmust use an absolute path.
🔧 Environment Variables
- 📁 DATA_DIR: Directory for storing task data (absolute path required)
- 🧠 ENABLE_THOUGHT_CHAIN: Controls detailed thinking process (default: true)
- 🌐 TEMPLATES_USE: Template language (default: en)
- 🖥️ ENABLE_GUI: Enables web interface (default: false)
- 📝 ENABLE_DETAILED_MODE: Shows conversation history (default: false)
🛠️ Tools Overview
| Category | Tool | Description |
|---|---|---|
| 📋 Planning | plan_task |
Start planning tasks |
analyze_task |
Analyze requirements | |
process_thought |
Step-by-step reasoning | |
reflect_task |
Improve solution concepts | |
init_project_rules |
Set project standards | |
| 🧩 Management | split_tasks |
Break into subtasks |
list_tasks |
Show all tasks | |
query_task |
Search tasks | |
get_task_detail |
Show task details | |
delete_task |
Remove tasks | |
| ▶️ Execution | execute_task |
Run specific tasks |
verify_task |
Verify completion | |
complete_task |
Mark as completed |
🤖 Recommended Models
- 👑 Claude 3.7: Offers strong understanding and generation capabilities
- 💎 Gemini 2.5: Google's latest model, performs excellently
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
📚 Documentation
⭐ Star History
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。
