Localstack

Name: Localstack
Author: giovanemartins

作者：giovanemartins版本 1.1.5i★ –i在你的电脑上运行

注册名称io.github.giovanemartins/localstack

安装

概览

作者提供的说明（英文原文）

MCP server for LocalStack AWS services, enabling AI agents to interact with local AWS infra.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 开发者工具
你需要填写：AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： LOCALSTACK_ENDPOINT, AWS_REGION, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "localstack": {
      "command": "npx",
      "args": [
        "-y",
        "@giovane.martins/localstack"
      ],
      "env": {
        "LOCALSTACK_ENDPOINT": "your-value",
        "AWS_REGION": "your-value",
        "AWS_ACCESS_KEY_ID": "your-value",
        "AWS_SECRET_ACCESS_KEY": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add localstack --env LOCALSTACK_ENDPOINT=your-value --env AWS_REGION=your-value --env AWS_ACCESS_KEY_ID=your-value --env AWS_SECRET_ACCESS_KEY=your-value -- npx -y @giovane.martins/localstack

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "localstack": {
      "command": "npx",
      "args": [
        "-y",
        "@giovane.martins/localstack"
      ],
      "env": {
        "LOCALSTACK_ENDPOINT": "your-value",
        "AWS_REGION": "your-value",
        "AWS_ACCESS_KEY_ID": "your-value",
        "AWS_SECRET_ACCESS_KEY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "localstack": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@giovane.martins/localstack"
      ],
      "env": {
        "LOCALSTACK_ENDPOINT": "your-value",
        "AWS_REGION": "your-value",
        "AWS_ACCESS_KEY_ID": "your-value",
        "AWS_SECRET_ACCESS_KEY": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

LOCALSTACK_ENDPOINT env
LocalStack endpoint URL
AWS_REGION env
AWS region
AWS_ACCESS_KEY_ID 机密 env
AWS access key ID
AWS_SECRET_ACCESS_KEY 机密 env
AWS secret access key

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 giovanemartins 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“开发者工具”中的其他服务器比较i

星标数多于此分类中其他 1385 个服务器的 0%
发布到注册中心的时间比此分类中其他 1385 个服务器的 9% 更新
基础检查结果等于或优于此分类中其他 1385 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Localstack 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

你需要填写：AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.1.5）于8个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它？

同一分类中有：GitHub, Desktop Commander, Cloudflare MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

GitHub

作者：github

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

电脑或云端★ 34,245MIT3天前更新

安装

Desktop Commander

作者：wonderwhy-er

MCP server for terminal commands, file operations, and process management

在你的电脑上运行★ 10,225MIT15天前更新

安装

Cloudflare MCP

作者：cloudflare

Cloudflare MCP servers

在云端运行★ 4,446Apache-2.014个月前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

LocalStack MCP Server

MCP server that exposes LocalStack-managed AWS services as AI-agent tools, enabling LLMs and AI agents to interact with local AWS infrastructure during development and testing.

Installation

The server is published to npm and the MCP Registry. No local build needed.

npm install -g @giovane.martins/localstack

Or run directly with npx (no install required):

npx @giovane.martins/localstack

Requirements

Node.js 20+
Docker (for LocalStack)

Local Development

# 1. Start LocalStack

docker compose up -d

2. Install dependencies

pnpm install

3. Build

pnpm run build

4. Run

pnpm start

Configuration

All configuration is via environment variables:

Variable	Default	Description
`LOCALSTACK_ENDPOINT`	`http://localhost:4566`	LocalStack base URL
`AWS_REGION`	`us-east-1`	AWS region
`AWS_ACCESS_KEY_ID`	`test`	Fake credentials for LocalStack
`AWS_SECRET_ACCESS_KEY`	`test`	Fake credentials for LocalStack

Running Tests

Requires LocalStack running (docker compose up -d).

pnpm test

MCP Client Configuration

Using the published npm package (recommended)

Add to your MCP client config (e.g. ~/.config/claude/claude_desktop_config.json):

"mcpServers": { "localstack": { "command": "npx", "args": ["-y", "@giovane.martins/localstack"], "env": { "LOCALSTACK_ENDPOINT": "http://localhost:4566", "AWS_REGION": "us-east-1", "AWS_ACCESS_KEY_ID": "test", "AWS_SECRET_ACCESS_KEY": "test" } } } }

Using a local build

"mcpServers": { "localstack": { "command": "node", "args": ["/path/to/mcp-servers/localstack/dist/index.js"], "env": { "LOCALSTACK_ENDPOINT": "http://localhost:4566", "AWS_REGION": "us-east-1", "AWS_ACCESS_KEY_ID": "test", "AWS_SECRET_ACCESS_KEY": "test" } } } }

Using `tsx` for development (no build step)

"mcpServers": { "localstack": { "command": "npx", "args": ["tsx", "/path/to/mcp-servers/localstack/src/index.ts"], "env": { "LOCALSTACK_ENDPOINT": "http://localhost:4566", "AWS_REGION": "us-east-1", "AWS_ACCESS_KEY_ID": "test", "AWS_SECRET_ACCESS_KEY": "test" } } } }

Available Tools

S3

Tool	Description
`s3_list_buckets`	List all S3 buckets
`s3_create_bucket`	Create a bucket
`s3_delete_bucket`	Delete a bucket
`s3_put_object`	Upload an object (text/JSON content)
`s3_get_object`	Download an object as text
`s3_delete_object`	Delete an object
`s3_list_objects`	List objects with optional prefix filter

SQS

Tool	Description
`sqs_list_queues`	List all queues
`sqs_create_queue`	Create a standard or FIFO queue
`sqs_delete_queue`	Delete a queue
`sqs_send_message`	Send a message
`sqs_receive_messages`	Receive up to 10 messages (with long-polling support)
`sqs_delete_message`	Delete a message by receipt handle
`sqs_purge_queue`	Purge all messages from a queue

SNS

Tool	Description
`sns_list_topics`	List all topics
`sns_create_topic`	Create a standard or FIFO topic
`sns_delete_topic`	Delete a topic
`sns_subscribe`	Subscribe an endpoint to a topic
`sns_unsubscribe`	Unsubscribe from a topic
`sns_list_subscriptions_by_topic`	List all subscriptions for a topic
`sns_publish`	Publish a message to a topic

EventBridge

Tool	Description
`eventbridge_list_buses`	List all event buses
`eventbridge_create_bus`	Create a custom event bus
`eventbridge_delete_bus`	Delete a custom event bus
`eventbridge_list_rules`	List rules on a bus
`eventbridge_put_rule`	Create or update a rule (event pattern or schedule)
`eventbridge_delete_rule`	Delete a rule
`eventbridge_describe_rule`	Describe a rule
`eventbridge_enable_rule`	Enable a rule
`eventbridge_disable_rule`	Disable a rule
`eventbridge_put_targets`	Add or update rule targets
`eventbridge_list_targets`	List targets for a rule
`eventbridge_remove_targets`	Remove targets from a rule
`eventbridge_put_events`	Send custom events to a bus (max 10)

Kinesis

Tool	Description
`kinesis_list_streams`	List all streams
`kinesis_create_stream`	Create a stream
`kinesis_delete_stream`	Delete a stream
`kinesis_describe_stream`	Describe a stream (status, shards)
`kinesis_put_record`	Put a single record
`kinesis_put_records`	Put multiple records (max 500)
`kinesis_get_records`	Get records from a shard

DynamoDB

Tool	Description
`dynamodb_list_tables`	List all tables
`dynamodb_create_table`	Create a table (partition key + optional sort key)
`dynamodb_delete_table`	Delete a table
`dynamodb_describe_table`	Describe a table
`dynamodb_put_item`	Put (create or replace) an item
`dynamodb_get_item`	Get an item by key
`dynamodb_delete_item`	Delete an item by key
`dynamodb_scan`	Scan all items (with optional filter expression)
`dynamodb_query`	Query by key condition

Lambda

Tool	Description
`lambda_list_functions`	List all functions
`lambda_get_function`	Get function details
`lambda_create_function`	Create a function from a base64-encoded ZIP
`lambda_delete_function`	Delete a function
`lambda_invoke`	Invoke a function and return its response + logs

Secrets Manager

Tool	Description
`secretsmanager_list_secrets`	List all secrets
`secretsmanager_create_secret`	Create a new secret
`secretsmanager_get_secret`	Get the value of a secret
`secretsmanager_update_secret`	Update the value of a secret
`secretsmanager_describe_secret`	Describe secret metadata
`secretsmanager_delete_secret`	Delete a secret (with optional force delete)
`secretsmanager_restore_secret`	Restore a previously deleted secret

SSM Parameter Store

Tool	Description
`ssm_get_parameter`	Get a parameter by name
`ssm_put_parameter`	Create or update a parameter
`ssm_delete_parameter`	Delete a parameter
`ssm_delete_parameters`	Delete up to 10 parameters in batch
`ssm_get_parameters_by_path`	Get all parameters under a path prefix
`ssm_describe_parameters`	List and describe parameters

SES

Tool	Description
`ses_list_identities`	List all verified identities
`ses_verify_email_identity`	Verify an email address
`ses_get_identity_verification_attributes`	Get verification status for identities
`ses_delete_identity`	Delete an identity
`ses_send_email`	Send an email (plain text and/or HTML)

Use Cases

Dev environment bootstrap — create S3 buckets, SQS queues, DynamoDB tables, and SSM parameters in one shot from a spec
Test data seeding — populate DynamoDB or S3 before running integration tests
Event-driven debugging — publish to EventBridge/SNS/Kinesis and inspect downstream effects without leaving the IDE
Secret/config management — read and update Secrets Manager / SSM values during local debug sessions
Lambda smoke testing — invoke Lambda functions, capture responses and logs, iterate quickly
Queue drain / inspect — receive and inspect SQS messages without a consumer running

Project Structure

localstack/

├── docker-compose.yml # LocalStack container ├── package.json ├── tsconfig.json ├── vitest.config.ts ├── src/ │ ├── index.ts # MCP server entry point │ ├── config.ts # Environment config │ ├── tools/ # One file per AWS service │ │ ├── s3.ts │ │ ├── sqs.ts │ │ ├── sns.ts │ │ ├── eventbridge.ts │ │ ├── kinesis.ts │ │ ├── dynamodb.ts │ │ ├── lambda.ts │ │ ├── secretsmanager.ts │ │ ├── ssm.ts │ │ └── ses.ts │ └── utils/ │ ├── client.ts # Shared AWS client factory (LocalStack endpoint) │ └── errors.ts # Standardised MCP error formatting └── tests/ # Integration tests (real LocalStack) ├── s3.test.ts ├── sqs.test.ts ├── sns.test.ts ├── eventbridge.test.ts ├── kinesis.test.ts ├── dynamodb.test.ts ├── lambda.test.ts ├── secretsmanager.test.ts ├── ssm.test.ts └── ses.test.ts