atlas-mcp-server
Atlas MCP Server
mongodb-labs
README
Atlas MCP Server
A Model Context Protocol server for interacting with MongoDB Atlas. This project implements a Model Context Protocol (MCP) server enabling AI assistants to interact with MongoDB Atlas resources through natural language.
📚 Table of Contents
🚀 Getting Started
Prerequisites
- Node.js (v23 or later)
- MongoDB Atlas account
Installation
# Clone the repository
git clone https://github.com/mongodb-labs/mongodb-mcp-server.git
cd mongodb-mcp-server
# Install dependencies
npm install
Running the MCP Server
npm run build
🛠️ Supported Tools
Tool List
auth
- Authenticate to MongoDB Atlaslist-clusters
- Lists MongoDB Atlas clusterslist-projects
- Lists MongoDB Atlas projects
👩💻 Client Integration (Use the server!)
VSCode
Prerequisites:
- Use VSCode Insiders (https://code.visualstudio.com/insiders/)
- Setup copilot in VSCode Insiders
Step 1: Add the mcp server to VSCode configuration
- Press
Cmd + Shift + P
and typeMCP: Add MCP Server
and select it. - Select the first option for a local MCP server.
- Add the path to dist/index.js in the prompt
Step 2: Verify the created mcp file
It should look like this
{
"servers": {
"mongodb-mcp-server": {
"type": "stdio",
"command": "/Users/<user>/workplace/atlas-mcp-server/dist/index.js",
"args": []
}
}
}
Step 3: Open the copilot chat and check that the toolbox icon is visible and has the mcp server listed.
Step 4: Try running a command
- Can you list my clusters?
Claude
Step 1: Install claude and login
brew install claude
Step 2: Create a configuration file for your MCP server
Open the file
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Paste the mcp server configuration into the file
{
"mcpServers": {
"Demo": {
"command": "path/to/this/repo/atlas-mc-server/dist/index.js"
}
}
}
Step 3: Launch Claude Desktop and click on the hammer icon, the Demo MCP server should be detected. Type in the chat "show me a demo of MCP" and allow the tool to get access.
- Detailed instructions with screenshots can be found in this document.
Note: If you make changes to your MCP server code, rebuild the project with npm run build
and restart the server and Claude Desktop.
🤝 Contributing
Interested in contributing? Great! Please check our Contributing Guide for guidelines on code contributions, standards, adding new tools, and troubleshooting information.
推荐服务器
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Claude Code MCP
一个实现了 Claude Code 作为模型上下文协议(Model Context Protocol, MCP)服务器的方案,它可以通过标准化的 MCP 接口来使用 Claude 的软件工程能力(代码生成、编辑、审查和文件操作)。
@kazuph/mcp-taskmanager
用于任务管理的模型上下文协议服务器。它允许 Claude Desktop(或任何 MCP 客户端)在基于队列的系统中管理和执行任务。
MCP Package Docs Server
促进大型语言模型高效访问和获取 Go、Python 和 NPM 包的结构化文档,通过多语言支持和性能优化来增强软件开发。
mermaid-mcp-server
一个模型上下文协议 (MCP) 服务器,用于将 Mermaid 图表转换为 PNG 图像。
Jira-Context-MCP
MCP 服务器向 AI 编码助手(如 Cursor)提供 Jira 工单信息。

Linear MCP Server
一个模型上下文协议(Model Context Protocol)服务器,它与 Linear 的问题跟踪系统集成,允许大型语言模型(LLM)通过自然语言交互来创建、更新、搜索和评论 Linear 问题。

Sequential Thinking MCP Server
这个服务器通过将复杂问题分解为顺序步骤来促进结构化的问题解决,支持修订,并通过完整的 MCP 集成来实现多条解决方案路径。
Curri MCP Server
通过管理文本笔记、提供笔记创建工具以及使用结构化提示生成摘要,从而实现与 Curri API 的交互。