Sequential Questioning MCP Server
顺序提问 MCP 服务器
一个专用服务器,使 LLM(大型语言模型)能够通过顺序查询收集特定信息。该项目实现了 MCP(模型控制协议)标准,可与 LLM 客户端无缝集成。
项目状态
🎉 1.0.0 版本发布🎉
顺序查询 MCP 服务器现已完成,并准备好投入生产部署。所有计划的功能均已实现、测试并记录。
Related MCP server: MCP Thinking Server
特征
顺序提问引擎:根据先前的回答生成适合上下文的后续问题
MCP 协议支持:完全实现 MCP 规范,以便与 LLM 集成
强大的 API :具有全面验证和错误处理的 RESTful API
矢量数据库集成:高效存储和检索问题模式
全面监控:使用 Prometheus 和 Grafana 实现性能指标和可观察性
生产就绪部署:具有多环境支持的 Kubernetes 部署配置
高可用性:水平 Pod 自动缩放器和 Pod 中断预算,确保生产可靠性
安全性:限制流量和保护应用程序的网络策略
文档
入门
先决条件
Python 3.10+
Docker 和 Docker Compose(用于本地开发)
Kubernetes 集群(用于生产部署)
PostgreSQL 15.4+
访问 Qdrant 实例
快速入门
最简单的开始方式是使用我们的初始化脚本:
./scripts/initialize_app.sh该脚本将:
检查 Docker 是否正在运行
使用 Docker Compose 启动所有必要的容器
自动运行数据库迁移
提供有关如何访问应用程序的信息
该应用程序将在http://localhost:8001上可用
本地开发
克隆存储库
git clone https://github.com/your-organization/sequential-questioning.git cd sequential-questioning安装依赖项
pip install -e ".[dev]"设置环境变量
cp .env.example .env # Edit .env file with your configuration运行开发服务器
uvicorn app.main:app --reload
Docker 部署
docker-compose up -d数据库设置
如果您手动启动应用程序,请不要忘记运行数据库迁移:
export DATABASE_URL="postgresql://postgres:postgres@localhost:5432/postgres"
bash scripts/run_migrations.shKubernetes 部署
开发环境
kubectl apply -k k8s/overlays/dev暂存环境
kubectl apply -k k8s/overlays/staging生产环境
kubectl apply -k k8s/overlays/prod
监控
访问 Prometheus 和 Grafana 仪表板进行监控:
kubectl port-forward -n monitoring svc/prometheus 9090:9090
kubectl port-forward -n monitoring svc/grafana 3000:3000CI/CD 管道
使用 GitHub Actions 实现自动化 CI/CD 管道:
持续集成:Linting、类型检查和测试
持续部署:自动部署到开发、准备和生产环境
部署验证:部署后自动检查
测试
运行测试套件:
pytest运行性能测试:
python -m tests.performance.test_sequential_questioning_load故障排除
未创建数据库表
如果应用程序正在运行但数据库表不存在:
确保数据库容器正在运行
手动运行数据库迁移:
export DATABASE_URL="postgresql://postgres:postgres@localhost:5432/postgres" bash scripts/run_migrations.sh
Pydantic 版本兼容性
如果遇到错误pydantic.errors.PydanticImportError: BaseSettings has been moved to the pydantic-settings package ,请确保:
pydantic-settings包包含在你的依赖项中您正在从
pydantic_settings导入BaseSettings,而不是直接从pydantic导入
该项目使用 Pydantic v2.x,它将BaseSettings移至单独的包中。
贡献
欢迎贡献!请参阅CONTRIBUTING.md获取相关指南。
执照
接触
如需支持或咨询,请联系support@example.com
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
MCP server for building and testing AI agents with multi-model experimentation and insights.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseAqualityCmaintenanceAn MCP server that enables users to query, compare, and synthesize responses from multiple local and cloud LLMs simultaneously using existing subscriptions. It provides tools for parallel model evaluation, consensus polling with an LLM-as-judge, and response synthesis across different model providers.81515MIT
- AlicenseNot gradedqualityDmaintenanceA powerful MCP server that enhances LLMs with advanced sequential thinking capabilities, supporting 19 thinking modes for structured reasoning and complex cognitive tasks.17MIT
- AlicenseNot gradedqualityDmaintenanceProduction-ready MCP server enabling LLM text generation, template management, context-aware conversations, and memory storage with enterprise quality assurance.212MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that dynamically extracts and manages user memory from LLM conversations, enabling consistent personalization across different models.7-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bitgeese/sequential-questioning'
If you have feedback or need assistance with the MCP directory API, please join our Discord server