Decision Tree MCP Server
dt_mcp 服务器(决策树和任务管理 MCP 服务器)
该项目实现了一个基于 Node.js 的模型上下文协议 (MCP) 服务器,用于管理和与.rtdq文件中定义的决策树进行交互,并处理基本的待办事项列表。它使用 Redis 作为后端,用于存储已解析的.rtdq数据和待办事项列表。
特征
RTDQ 处理:
从指定目录加载
.rtdq文件(v2.1 格式)。异步解析
.rtdq文件。将解析后的决策树数据存储在 Redis 中。
提供 MCP 工具(
get_dt_node_from_redis)来从加载的树中检索特定节点。
待办事项管理:
提供 MCP 工具(
add_todo、list_todos、mark_todo_done)来管理简单的待办事项列表。将待办事项存储在 Redis 中。
MCP 集成:
充当标准 MCP 服务器。
通过
/mcp端点上的 HTTP 服务器发送事件 (SSE) 进行通信。通过标准 MCP
tools/list和tools/call方法公开功能。
Related MCP server: Todo MCP Server
先决条件
Node.js(建议使用 v16+ 版本,用于 ES 模块和顶层 await)
npm(或 yarn)
Redis 服务器正在运行并可访问
设置
克隆存储库:
git clone <your-repo-url> cd dt-mcp-server安装依赖项:
npm install**配置环境:**在项目根目录中创建一个
.env文件(并将其添加到.gitignore)或设置环境变量:REDIS_URL:Redis 服务器的连接 URL(例如,redis://localhost:6379)。默认为redis://localhost:6379。RTDQ_DIR:(可选)包含.rtdq文件的目录的绝对路径。默认为项目内名为rtdq_files的子目录。PORT:(可选)服务器监听的端口。默认为3000。
**创建 RTDQ 目录:**确保
RTDQ_DIR指定的目录(或默认的rtdq_files子目录)存在。请将您的.rtdq文件放入其中。
运行服务器
npm startThis 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 Servers
- AlicenseAqualityDmaintenanceAn MCP server that allows AI assistants to manage todo lists stored in a simple markdown file, supporting creation, reading, updating, and deletion of todo items with persistent IDs.5146MIT
- FlicenseNot gradedqualityDmaintenanceThis MCP server provides tools to manage a todo list with CRUD operations, enabling listing, creating, updating, and deleting todos.
- AlicenseNot gradedqualityCmaintenanceA Node.js MCP server example with user management, task management, and calculator tools. Supports authentication via bearer token and can be deployed locally or via Docker.7MIT
- FlicenseNot gradedqualityDmaintenanceA multi-node todo application server using MCP protocol, Redis for storage, and OpenRouter for AI-powered prioritization analysis.
Related MCP Connectors
Cloud-hosted MCP server for durable AI memory
Markdown-first MCP server for Notion API with 8 composite tools and 39 actions.
MCP server for AI dialogue using various LLM models via AceDataCloud
Appeared in Searches
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/psikosen/dt_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server