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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
