Sequential Thinking

AI 与智能体

by kiennd

通过结构化思考流程促进动态、反思式问题求解,将复杂问题拆解为步骤,并随理解深入修正思路、验证假设。

什么是 Sequential Thinking

通过结构化思考流程促进动态、反思式问题求解,将复杂问题拆解为步骤,并随理解深入修正思路、验证假设。

核心功能 (1 个工具)

sequentialthinking

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. 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 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 - Repeats the process until satisfied - Provides a correct answer 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 - 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 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. Repeat the process until satisfied with the solution 10. Provide a single, ideally correct answer as the final output 11. Only set next_thought_needed to false when truly done and a satisfactory answer is reached

README

Model Context Protocol servers

This repository is a collection of reference implementations for the Model Context Protocol (MCP), as well as references to community built servers and additional resources.

The servers in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources. Each MCP server is implemented with either the Typescript MCP SDK or Python MCP SDK.

Note: Lists in this README are maintained in alphabetical order to minimize merge conflicts when adding new items.

🌟 Reference Servers

These servers aim to demonstrate MCP features and the Typescript and Python SDK.

  • AWS KB Retrieval - Retrieval from AWS Knowledge Base using Bedrock Agent Runtime
  • Brave Search - Web and local search using Brave's Search API
  • EverArt - AI image generation using various models
  • Everything - Reference / test server with prompts, resources, and tools
  • Fetch - Web content fetching and conversion for efficient LLM usage
  • Filesystem - Secure file operations with configurable access controls
  • Git - Tools to read, search, and manipulate Git repositories
  • GitHub - Repository management, file operations, and GitHub API integration
  • GitLab - GitLab API, enabling project management
  • Google Drive - File access and search capabilities for Google Drive
  • Google Maps - Location services, directions, and place details
  • Memory - Knowledge graph-based persistent memory system
  • PostgreSQL - Read-only database access with schema inspection
  • Puppeteer - Browser automation and web scraping
  • Sentry - Retrieving and analyzing issues from Sentry.io
  • Sequential Thinking - Dynamic and reflective problem-solving through thought sequences
  • Slack - Channel management and messaging capabilities
  • Sqlite - Database interaction and business intelligence capabilities
  • Time - Time and timezone conversion capabilities

🤝 Third-Party Servers

🎖️ Official Integrations

Official integrations are maintained by companies building production ready MCP servers for their platforms.

  • <img height="12" width="12" src="https://axiom.co/favicon.ico" alt="Axiom Logo" /> Axiom - Query and analyze your Axiom logs, traces, and all other event data in natural language
  • <img height="12" width="12" src="https://browserbase.com/favicon.ico" alt="Browserbase Logo" /> Browserbase - Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)
  • <img height="12" width="12" src="https://cdn.simpleicons.org/cloudflare" /> Cloudflare - Deploy, configure & interrogate your resources on the Cloudflare developer platform (e.g. Workers/KV/R2/D1)
  • <img height="12" width="12" src="https://e2b.dev/favicon.ico" alt="E2B Logo" /> E2B - Run code in secure sandboxes hosted by E2B
  • <img height="12" width="12" src="https://exa.ai/images/favicon-32x32.png" alt="Exa Logo" /> Exa - Search Engine made for AIs by Exa
  • <img height="12" width="12" src="https://fireproof.storage/favicon.ico" alt="Fireproof Logo" /> Fireproof - Immutable ledger database with live synchronization
  • <img height="12" width="12" src="https://cdn.simpleicons.org/jetbrains" /> JetBrains – Work on your code with JetBrains IDEs
  • <img height="12" width="12" src="https://kagi.com/favicon.ico" alt="Kagi Logo" /> Kagi Search - Search the web using Kagi's search API
  • <img height="12" width="12" src="https://www.meilisearch.com/favicon.ico" alt="Meilisearch Logo" /> Meilisearch - Interact & query with Meilisearch (Full-text & semantic search API)
  • <img height="12" width="12" src="https://metoro.io/static/images/logos/Metoro.svg" /> Metoro - Query and interact with kubernetes environments monitored by Metoro
  • <img height="12" width="12" src="https://www.motherduck.com/favicon.ico" alt="MotherDuck Logo" /> MotherDuck - Query and analyze data with MotherDuck and local DuckDB
  • <img height="12" width="12" src="https://needle-ai.com/images/needle-logo-orange-2-rounded.png" alt="Needle AI Logo" /> Needle - Production-ready RAG out of the box to search and retrieve data from your own documents.
  • <img height="12" width="12" src="https://neo4j.com/favicon.ico" alt="Neo4j Logo" /> Neo4j - Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory
  • Neon - Interact with the Neon serverless Postgres platform
  • <img height="12" width="12" src="https://qdrant.tech/img/brand-resources-logos/logomark.svg" /> Qdrant - Implement semantic memory layer on top of the Qdrant vector search engine
  • Raygun - Interact with your crash reporting and real using monitoring data on your Raygun account
  • <img height="12" width="12" src="https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg" /> Search1API - One API for Search, Crawling, and Sitemaps
  • <img height="12" width="12" src="https://www.tinybird.co/favicon.ico" alt="Tinybird Logo" /> Tinybird - Interact with Tinybird serverless ClickHouse platform

🌎 Community Servers

A growing set of community-developed and maintained servers demonstrates various applications of MCP across different domains.

Note: Community servers are untested and should be used at your own risk. They are not affiliated with or endorsed by Anthropic.

  • AWS S3 - A sample MCP server for AWS S3 that flexibly fetches objects from S3 such as PDF documents
  • AWS - Perform operations on your AWS resources using an LLM
  • Airtable - Read and write access to Airtable databases, with schema inspection.
  • Airtable - Airtable Model Context Protocol Server.
  • AlphaVantage - MCP server for stock market data API AlphaVantage
  • Anki - An MCP server for interacting with your Anki decks and cards.
  • Any Chat Completions - Interact with any OpenAI SDK Compatible Chat Completions API like OpenAI, Perplexity, Groq, xAI and many more.
  • Atlassian - Interact with Atlassian Cloud products (Confluence and Jira) including searching/reading Confluence spaces/pages, accessing Jira issues, and project metadata.
  • BigQuery (by LucasHild) - This server enables LLMs to inspect database schemas and execute queries on BigQuery.
  • BigQuery (by ergut) - Server implementation for Google BigQuery integration that enables direct BigQuery database access and querying capabilities
  • ChatMCP – An Open Source Cross-platform GUI Desktop application compatible with Linux, macOS, and Windows, enabling seamless interaction with MCP servers across dynamically selectable LLMs, by AIQL
  • ChatSum - Query and Summarize chat messages with LLM. by mcpso
  • Chroma - Vector database server for semantic document search and metadata filtering, built on Chroma
  • Cloudinary - Cloudinary Model Context Protocol Server to upload media to Cloudinary and get back the media link and details.
  • cognee-mcp - GraphRAG memory server with customizable ingestion, data processing and search
  • coin_api_mcp - Provides access to coinmarketcap cryptocurrency data.
  • Contentful-mcp - Read, update, delete, publish content in your Contentful space(s) from this MCP Server.
  • Data Exploration - MCP server for autonomous data exploration on .csv-based datasets, providing intelligent insights with minimal effort. NOTE: Will execute arbitrary Python code on your machine, please use with caution!
  • Dataset Viewer - Browse and analyze Hugging Face datasets with features like search, filtering, statistics, and data export
  • DevRev - An MCP server to integrate with DevRev APIs to search through your DevRev Knowledge Graph where objects can be imported from diff. sources listed here.
  • Dify - A simple implementation of an MCP server for dify workflows.
  • Docker - Integrate with Docker to manage containers, images, volumes, and networks.
  • Drupal - Server for interacting with Drupal using STDIO transport layer.
  • Elasticsearch - MCP server implementation that provides Elasticsearch interaction.
  • Fetch - A server that flexibly fetches HTML, JSON, Markdown, or plaintext.
  • FireCrawl - Advanced web scraping with JavaScript rendering, PDF support, and smart rate limiting
  • FlightRadar24 - A Claude Desktop MCP server that helps you track flights in real-time using Flightradar24 data.
  • Glean - A server that uses Glean API to search and chat.
  • Google Calendar - Integration with Google Calendar to check schedules, find time, and add/delete events
  • Google Tasks - Google Tasks API Model Context Protocol Server.
  • Home Assistant - Interact with Home Assistant including viewing and controlling lights, switches, sensors, and all other Home Assistant entities.
  • HuggingFace Spaces - Server for using HuggingFace Spaces, supporting Open Source Image, Audio, Text Models and more. Claude Desktop mode for easy integration.
  • Inoyu - Interact with an Apache Unomi CDP customer data platform to retrieve and update customer profiles
  • Keycloak MCP - This MCP server enables natural language interaction with Keycloak for user and realm management including creating, deleting, and listing users and realms.
  • Kubernetes - Connect to Kubernetes cluster and manage pods, deployments, and services.
  • Linear - Allows LLM to interact with Linear's API for project management, including searching, creating, and updating issues.
  • LlamaCloud (by marcusschiesser) - Integrate the data stored in a managed index on LlamaCloud
  • MCP Installer - This server is a server that installs other MCP servers for you.
  • mcp-k8s-go - Golang-based Kubernetes server for MCP to browse pods and their logs, events, namespaces and more. Built to be extensible.
  • MSSQL - MSSQL database integration with configurable access controls and schema inspection
  • Markdownify - MCP to convert almost anything to Markdown (PPTX, HTML, PDF, Youtube Transcripts and more)
  • Minima - MCP server for RAG on local files
  • MongoDB - A Model Context Protocol Server for MongoDB.
  • MySQL (by benborla) - MySQL database integration in NodeJS with configurable access controls and schema inspection
  • MySQL (by DesignComputer) - MySQL database integration in Python with configurable access controls and schema inspection
  • NS Travel Information - Access Dutch Railways (NS) real-time train travel information and disruptions through the official NS API.
  • Notion (by suekou) - Interact with Notion API.
  • Notion (by v-3) - Notion MCP integration. Search, Read, Update, and Create pages through Claude chat.
  • oatpp-mcp - C++ MCP integration for Oat++. Use Oat++ to build MCP servers.
  • Obsidian Markdown Notes - Read and search through your Obsidian vault or any directory containing Markdown notes
  • OpenAPI - Interact with OpenAPI APIs.
  • OpenCTI - Interact with OpenCTI platform to retrieve threat intelligence data including reports, indicators, malware and threat actors.
  • OpenRPC - Interact with and discover JSON-RPC APIs via OpenRPC.
  • Pandoc - MCP server for seamless document format conversion using Pandoc, supporting Markdown, HTML, and plain text, with other formats like PDF, csv and docx in development.
  • Pinecone - MCP server for searching and uploading records to Pinecone. Allows for simple RAG features, leveraging Pinecone's Inference API.
  • Placid.app - Generate image and video creatives using Placid.app templates
  • Playwright - This MCP Server will help you run browser automation and webscraping using Playwright
  • Postman - MCP server for running Postman Collections locally via Newman. Allows for simple execution of Postman Server and returns the results of whether the collection passed all the tests.
  • RAG Web Browser An MCP server for Apify's RAG Web Browser Actor to perform web searches, scrape URLs, and return content in Markdown.
  • Rememberizer AI - An MCP server designed for interacting with the Rememberizer data source, facilitating enhanced knowledge retrieval.
  • Salesforce MCP - Interact with Salesforce Data and Metadata
  • Scholarly - A MCP server to search for scholarly and academic articles.
  • Snowflake - This MCP server enables LLMs to interact with Snowflake databases, allowing for secure and controlled data operations.
  • Spotify - This MCP allows an LLM to play and use Spotify.
  • TMDB - This MCP server integrates with The Movie Database (TMDB) API to provide movie information, search capabilities, and recommendations.
  • Tavily search - An MCP server for Tavily's search & news API, with explicit site inclusions/exclusions
  • Todoist - Interact with Todoist to manage your tasks.
  • Vega-Lite - Generate visualizations from fetched data using the VegaLite format and renderer.
  • Windows CLI - MCP server for secure command-line interactions on Windows systems, enabling controlled access to PowerShell, CMD, and Git Bash shells.
  • X (Twitter) (by EnesCinr) - Interact with twitter API. Post tweets and search for tweets by query.
  • X (Twitter) (by vidhupv) - Create, manage and publish X/Twitter posts directly through Claude chat.
  • XMind - Read and search through your XMind directory containing XMind files.

📚 Frameworks

These are high-level frameworks that make it easier to build MCP servers.

📚 Resources

Additional resources on MCP.

🚀 Getting Started

Using MCP Servers in this Repository

Typescript-based servers in this repository can be used directly with npx.

For example, this will start the Memory server:

sh
npx -y @modelcontextprotocol/server-memory

Python-based servers in this repository can be used directly with uvx or pip. uvx is recommended for ease of use and setup.

For example, this will start the Git server:

sh
# With uvx
uvx mcp-server-git

# With pip
pip install mcp-server-git
python -m mcp_server_git

Follow these instructions to install uv / uvx and these to install pip.

Using an MCP Client

However, running a server on its own isn't very useful, and should instead be configured into an MCP client. For example, here's the Claude Desktop configuration to use the above server:

json
{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-memory"]
    }
  }
}

Additional examples of using the Claude Desktop as an MCP client might look like:

json
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/files"]
    },
    "git": {
      "command": "uvx",
      "args": ["mcp-server-git", "--repository", "path/to/git/repo"]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    },
    "postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost/mydb"]
    }
  }
}

🛠️ Creating Your Own Server

Interested in creating your own MCP server? Visit the official documentation at modelcontextprotocol.io for comprehensive guides, best practices, and technical details on implementing MCP servers.

🤝 Contributing

See CONTRIBUTING.md for information about contributing to this repository.

🔒 Security

See SECURITY.md for reporting security vulnerabilities.

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.

💬 Community

⭐ Support

If you find MCP servers useful, please consider starring the repository and contributing new servers or improvements!


Managed by Anthropic, but built together with the community. The Model Context Protocol is open source and we encourage everyone to contribute their own servers and improvements!

常见问题

Sequential Thinking 是什么?

通过结构化思考流程促进动态、反思式问题求解,将复杂问题拆解为步骤,并随理解深入修正思路、验证假设。

Sequential Thinking 提供哪些工具?

提供 1 个工具,包括 sequentialthinking

相关 Skills

Claude接口

by anthropics

Universal
热门

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。

想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心

AI 与智能体
未扫描114.1k

RAG架构师

by alirezarezvani

Universal
热门

聚焦生产级RAG系统设计与优化,覆盖文档切块、检索链路、索引构建、召回评估等关键环节,适合搭建可扩展、高准确率的知识库问答与检索增强应用。

面向RAG落地,把知识库、向量检索和生成链路系统串联起来,做架构设计时更清晰,也更少踩坑。

AI 与智能体
未扫描10.2k

计算机视觉

by alirezarezvani

Universal
热门

聚焦目标检测、图像分割与视觉系统落地,覆盖 YOLO、DETR、Mask R-CNN、SAM 等方案,适合定制数据集训练、推理优化及 ONNX/TensorRT 部署。

把目标检测、图像分割到推理部署串成完整工程链路,主流框架与 YOLO、DETR、SAM 等方案都覆盖,落地视觉 AI 会省心很多。

AI 与智能体
未扫描10.2k

相关 MCP Server

顺序思维

编辑精选

by Anthropic

热门

Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。

这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。

AI 与智能体
83.4k

知识图谱记忆

编辑精选

by Anthropic

热门

Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。

帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。

AI 与智能体
83.4k

PraisonAI

编辑精选

by mervinpraison

热门

PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。

如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。

AI 与智能体
6.8k

评论