
LocalStack MCP Server
A Model Context Protocol (MCP) server for LocalStack that enables management of local AWS development environments, including container lifecycle operations, infrastructure deployments, log analysis with IAM policy generation, chaos injection, and Cloud Pods state management.
README
LocalStack MCP Server
A Model Context Protocol server that provides tools to manage your LocalStack container and other assorted related tasks, to simplify local cloud development and testing. The LocalStack MCP Server provides simplified integration between Model Context Protocol-compatible apps and your local AWS development environment, enabling secure and direct communication with LocalStack's assortment of various features.
This server eliminates custom scripts and manual LocalStack management with direct access to:
- Start, stop, restart, and monitor LocalStack container status with built-in auth.
- Deploy CDK and Terraform projects with automatic configuration detection.
- Parse logs, catch errors, and auto-generate IAM policies from violations.
- Inject chaos faults and network effects into LocalStack to test system resilience.
- Manage LocalStack state snapshots via Cloud Pods for development workflows.
- Connect AI assistants and dev tools for automated cloud testing workflows.
Tools Reference
This server provides your AI with dedicated tools for managing your LocalStack environment:
Tool Name | Description | Key Features |
---|---|---|
localstack-management |
Manages LocalStack container operations and settings | - Execute start, stop, restart, and status checks<br/>- Integrate LocalStack Pro authentication tokens<br/>- Inject custom environment variables<br/>- Verify real-time status and perform health monitoring |
localstack-deployer |
Handles infrastructure deployment to LocalStack environments | - Automatically run CDK and Terraform tooling to deploy infrastructure locally<br/>- Enable parameterized deployments with variable support<br/>- Process and present deployment results<br/>- Requires you to have cdklocal or tflocal installed in your system path |
localstack-logs-analysis |
Analyzes LocalStack logs for troubleshooting and insights | - Offer multiple analysis options including summaries, errors, requests, and raw data<br/>- Filter by specific services and operations<br/>- Generate API call metrics and failure breakdowns<br/>- Group errors intelligently and identify patterns |
localstack-iam-policy-analyzer |
Handles IAM policy management and violation remediation | - Set IAM enforcement levels including enforced , soft , and disabled modes<br/>- Search logs for permission-related violations<br/>- Generate IAM policies automatically from detected access failures<br/>- Requires a valid LocalStack Auth Token |
localstack-chaos-injector |
Injects and manages chaos engineering faults for system resilience testing | - Inject, add, remove, and clear service fault rules<br/>- Configure network latency effects<br/>- Comprehensive fault targeting by service, region, and operation<br/>- Built-in workflow guidance for chaos experiments |
localstack-cloud-pods |
Manages LocalStack state snapshots for development workflows | - Save current state as Cloud Pods<br/>- Load previously saved Cloud Pods instantly<br/>- Delete Cloud Pods or reset to a clean state<br/>- Requires a valid LocalStack Auth Token |
Installation
Editor | Installation |
---|---|
Cursor | |
For other MCP Clients, refer to the configuration guide. |
Prerequisites
- LocalStack CLI and Docker installed in your system path
cdklocal
ortflocal
installed in your system path for running infrastructure deployment tooling- A valid LocalStack Auth Token to enable Pro services IAM Policy Analyzer, Cloud Pods, and Chaos Injector tools (optional)
- Node.js v22.x installed in your system path
Configuration
Add the following to your MCP client's configuration file (e.g., ~/.cursor/mcp.json
). This configuration uses npx
to run the server, which will automatically download & install the package if not already present:
{
"mcpServers": {
"localstack-mcp-server": {
"command": "npx",
"args": ["-y", "@localstack/localstack-mcp-server"]
}
}
}
If you installed from source, change command
and args
to point to your local build:
{
"mcpServers": {
"localstack-mcp-server": {
"command": "node",
"args": ["/path/to/your/localstack-mcp-server/dist/stdio.js"]
}
}
}
Enabling Licensed Features
To activate LocalStack licensed features, you need to add your LocalStack Auth Token to the environment variables. You can get your LocalStack Auth Token by following the official documentation.
Here's how to add your LocalStack Auth Token to the environment variables:
{
"mcpServers": {
"localstack-mcp-server": {
"command": "npx",
"args": ["-y", "@localstack/localstack-mcp-server"],
"env": {
"LOCALSTACK_AUTH_TOKEN": "<YOUR_TOKEN>"
}
}
}
}
Contributing
Pull requests are welcomed on GitHub! To get started:
- Install Git and Node.js
- Clone the repository
- Install dependencies with
yarn
- Build with
yarn build
Built on the XMCP framework, you can add new tools by adding a new file to the src/tools
directory and documenting it in the manifest.json
file.
License
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
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。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。