# Sequential Thinking (MCP Server)

> Structured, reflective step-by-step problem solving for LLMs

- Type: MCP server
- Publisher: Model Context Protocol (official)
- Categories: AI & ML
- Website: https://github.com/modelcontextprotocol/servers/tree/main/src/sequentialthinking
- Source: https://github.com/modelcontextprotocol/servers
- Transport: stdio
- Launch command: npx -y @modelcontextprotocol/server-sequential-thinking
- Sign-in: none
- GitHub stars: 90924
- Listed: 2024-12-01

## About

Reference MCP server providing a single tool for dynamic, revisable chains of thought. Models can break problems into steps, revise earlier thoughts and branch into alternative reasoning paths.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
   ```

   config.toml:

   ```toml
   [mcp_servers.sequential-thinking]
   command = "npx"
   args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="Sequential Thinking",
       params={"command": "npx", "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Think step by step through migrating our monolith to microservices")
       print(result.final_output)
   ```

## Tools

- `sequential_thinking`

## Example prompts

- "Think step by step through migrating our monolith to microservices"
- "Plan a database schema for a booking app, revising as needed"
- "Break down this ambiguous bug report into hypotheses"

## Related

- [Browser Use](https://chatgptplugins.directory/mcp/browser-use.md): Run Browser Use cloud browser agents or control a local browser over MCP
- [Memory](https://chatgptplugins.directory/mcp/memory.md): Knowledge graph-based persistent memory across conversations
- [Mem0](https://chatgptplugins.directory/mcp/mem0.md): Hosted long-term memory for AI agents and clients
- [Serena](https://chatgptplugins.directory/mcp/serena.md): Semantic code retrieval and editing toolkit for coding agents
- [Graphiti MCP](https://chatgptplugins.directory/mcp/graphiti.md): Temporal knowledge graph memory for agents, by Zep
- [OpenAI Docs MCP](https://chatgptplugins.directory/mcp/openai-docs.md): Search and read OpenAI's developer documentation from Codex or any MCP client

---
Source: https://chatgptplugins.directory/mcp/sequential-thinking · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.