Use Aws Mcp Server
by
Provides AWS CLI functionality through a standardized MCP interface, enabling portable use across various AI tools and environments.
Use Aws Mcp Server Overview
What is Use Aws Mcp Server about?
The server replicates the use_aws tool from the Amazon Q Developer CLI, exposing AWS CLI commands via the Model Context Protocol (MCP). It allows AI‑enabled applications to execute AWS operations safely and consistently without directly invoking the AWS CLI.
How to use Use Aws Mcp Server?
- Install the Rust crate:
cargo install use_aws_mcp. - Start the server locally:
./target/release/use_aws_mcp(the server communicates over stdin/stdout using JSON‑RPC). - Configure your MCP client with a JSON entry, for example:
{
"mcpServers": {
"use_aws_mcp": {
"name": "use_aws_mcp",
"command": "use_aws_mcp",
"timeout": 300,
"env": {},
"disabled": false
}
}
}
- Invoke the
use_awstool from the client by providing the required arguments (service, operation, region, etc.).
Key features of Use Aws Mcp Server
- Full AWS CLI integration with automatic parameter conversion to kebab‑case.
- Safety checks that differentiate read‑only and write operations, prompting for confirmation on destructive actions.
- Automatic user‑agent handling for proper AWS request tracking.
- Output truncation to keep responses under 100 KB.
- Human‑readable command descriptions with rich terminal formatting.
- Complete MCP compliance for seamless integration with any MCP‑compatible client.
Use cases of Use Aws Mcp Server
- AI coding assistants (e.g., Avante, Cursor) that need to retrieve AWS resources or perform infrastructure queries.
- Automation scripts that rely on language models to generate or validate AWS commands.
- Multi‑tool environments where developers switch between different AI assistants but want a consistent AWS interface.
- Security‑focused workflows that enforce read‑only defaults and require explicit approval for changes.
FAQ from the Use Aws Mcp Server
Q: Do I need the AWS CLI installed? A: Yes, the AWS CLI must be present and configured with valid credentials.
Q: Can I use this with non‑shell MCP clients like Cursor?
A: Non‑shell clients do not inherit environment variables automatically, so you should specify the profile_name in the request.
Q: How are large outputs handled? A: Responses exceeding 100 KB are truncated to prevent memory issues.
Q: What determines a read‑only operation?
A: Operations whose names start with get, describe, list, ls, search, or batch_get are considered read‑only.
Q: How do I enable debug logging?
A: Run the server with RUST_LOG=use_aws=debug ./target/release/use_aws_mcp.
Use Aws Mcp Server's README
use_aws MCP Server
🌟 amazon-q-cli is great, and it is great because it has use_aws MCP tool to interact with AWS API.
💡 Wouldn't it be greater if this use_aws was portable, and use it across different AI tools, whichever you're currently using?
⚡ use_aws_mcp is a standalone Model Context Protocol (MCP) server that provides AWS CLI functionality through a standardized interface.
This server replicates the functionality of the use_aws tool from the Amazon Q Developer CLI.
🎬 Demo
-
Usage with Avante, MCPHub in nvim
-
Usage with Cursor
✨ Features
- AWS CLI Integration: Execute AWS CLI commands with proper parameter handling
- Safety Checks: Automatic detection of read-only vs. write operations
- User Agent Management: Proper AWS CLI user agent setup for tracking
- Parameter Formatting: Automatic conversion of parameters to kebab-case for CLI compatibility
- Error Handling: Comprehensive error handling and output formatting
- MCP Protocol: Full Model Context Protocol compliance
- Human-Readable Descriptions: Rich command descriptions using terminal formatting
📦 Installation
📋 Prerequisites
- 🦀 Rust (1.70 or later), Cargo
- for MacOS and linux, install with
curl https://sh.rustup.rs -sSf | sh
- for MacOS and linux, install with
- ☁️ AWS CLI installed and configured
- 🔑 AWS credentials configured (via AWS CLI, environment variables, or IAM roles)
🔨 Building
cargo build --release
The binary will be available at target/release/use_aws.
🚀 Usage
🔗 MCP Client Integration
To use this server with an MCP client, first install it using Cargo:
cargo install use_aws_mcp
Then configure your MCP client with:
{
"mcpServers": {
"use_aws_mcp": {
"name": "use_aws_mcp",
"command": "use_aws_mcp",
"timeout": 300,
"env": {},
"disabled": false
}
}
}
⚠️ Important Caveat for Using MCP Client
With q cli, mcp clients are shell process, so credentials env like AWS_DEFAULT_PROFILE are automatically transfered to mcp server.
However, non shell mcp clients like cursor cannot take advantage of this, so it is best advised to require mcp clients directly to use specific aws profile.
📋 User Flow:
- Set mcp.json above
- Set API key, or login to specific profile using
aws sso login - Ask away mcp client aws related questions! and be sure to require it to use specific profile.
Running the MCP Server Locally
./target/release/use_aws_mcp
The server communicates via stdin/stdout using JSON-RPC protocol.
Command Descriptions
The server provides human-readable descriptions of AWS CLI commands. You can see this in action by running the example:
cargo run --example description_demo
This will output something like:
Running aws cli command:
Service name: s3
Operation name: list-buckets
Parameters:
- max-items: "10"
- query: "Buckets[].Name"
Profile name: development
Region: us-west-2
Label: List S3 buckets with query
✅ This command is read-only (no acceptance required)
🛠️ Tool Specification
The server provides a single tool called use_aws with the following schema:
{
"name": "use_aws",
"description": "Execute AWS CLI commands with proper parameter handling and safety checks",
"inputSchema": {
"type": "object",
"properties": {
"service_name": {
"type": "string",
"description": "AWS service name (e.g., s3, ec2, lambda)"
},
"operation_name": {
"type": "string",
"description": "AWS CLI operation name (e.g., list-buckets, describe-instances)"
},
"parameters": {
"type": "object",
"description": "Optional parameters for the AWS CLI command",
"additionalProperties": true
},
"region": {
"type": "string",
"description": "AWS region (e.g., us-west-2, eu-west-1)"
},
"profile_name": {
"type": "string",
"description": "Optional AWS profile name"
},
"label": {
"type": "string",
"description": "Optional label for the operation"
}
},
"required": ["service_name", "operation_name", "region"]
}
}
📚 Examples
List S3 Buckets
{
"name": "use_aws",
"arguments": {
"service_name": "s3",
"operation_name": "ls",
"region": "us-west-2"
}
}
Describe EC2 Instances
{
"name": "use_aws",
"arguments": {
"service_name": "ec2",
"operation_name": "describe-instances",
"region": "us-west-2",
"parameters": {
"instance-ids": "i-1234567890abcdef0"
}
}
}
List Lambda Functions with Profile
{
"name": "use_aws",
"arguments": {
"service_name": "lambda",
"operation_name": "list-functions",
"region": "us-west-2",
"profile_name": "development"
}
}
🛡️ Safety Features
Read-Only Operation Detection
The server automatically detects read-only operations based on the operation name prefix:
- Read-only prefixes:
get,describe,list,ls,search,batch_get - Write operations: All other operations require explicit user acceptance
Output Truncation
Large outputs are automatically truncated to prevent memory issues, with a maximum response size of 100KB.
Development
Running Tests
cargo test
🔨 Building for Development
cargo build
Running with Logging
RUST_LOG=use_aws=debug cargo run
Examples
# Run the description demo
cargo run --example description_demo
Architecture
The project is structured as follows:
src/lib.rs: Core library with types and constantssrc/error.rs: Error handling typessrc/use_aws.rs: Core AWS CLI functionality (replicated from original)src/mcp_server.rs: MCP server implementationsrc/main.rs: Binary entry pointexamples/description_demo.rs: Example demonstrating command descriptions
📦 Dependencies
If you do not have Cargo (the Rust package manager) installed, you can get it by installing Rust using rustup:
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
Follow the on-screen instructions to complete the installation. After installation, restart your terminal and ensure Cargo is available by running:
cargo --version
You should see the installed Cargo version printed.
This project is distributed as a Rust crate. The following dependencies are managed automatically by Cargo:
tokioserdeserde_jsoneyrebstrconvert_caseasync-traitthiserrortracingtracing-subscribercrossterm
test/dev dependencies:
tokio-test
You do not need to install these manually; Cargo will handle them during installation.
📄 License
MIT, Apache-2.0
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Submit a pull request
🔒 Security
This server executes AWS CLI commands, which may have security implications:
- Ensure proper AWS credentials and permissions
- Review all commands before execution
- Use read-only operations when possible
- Consider running in a restricted environment
🔧 Troubleshooting
Common Issues
- AWS CLI not found: Ensure AWS CLI is installed and in PATH
- Permission denied: Check AWS credentials and permissions
- Invalid region: Verify the region name is correct
- Parameter errors: Check parameter names and values
Debug Mode
Run with debug logging to see detailed information:
RUST_LOG=use_aws=debug ./target/release/use_aws
References
Use Aws Mcp Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Use Aws Mcp Server's Information
- Author
- runjivu
- Category
- Cloud Platforms
- Language
- Rust
- License
- Apache License 2.0
- Stars
- 1
- Updated
- 2 months ago
Configuration
{
"mcpServers": {
"use_aws_mcp": {
"command": "use_aws_mcp",
"args": [],
"env": {}
}
}
}Configure Clients
Related MCP Servers
Discover more MCP servers with similar functionality and use cases
Daytona
by daytonaio
Provides a secure, elastic sandbox environment for executing AI‑generated code with isolated runtimes and sub‑90 ms provisioning.
AWS MCP Servers
Officialby awslabs
Specialized servers that expose AWS capabilities through the Model Context Protocol, allowing AI assistants and other applications to retrieve up‑to‑date AWS documentation, manage infrastructure, query services, and perform workflow automation directly from their context.
AWS
Officialby awslabs
AWS MCP Servers allow AI agents to interact with and manage a wide range of AWS services using natural language commands. They enable AI-powered cloud management, automated DevOps, and data-driven insights within the AWS ecosystem.
Cloudflare MCP Server
by cloudflare
Remote Model Context Protocol endpoints that let AI clients read, process, and act on data across Cloudflare services such as Workers, Radar, Observability, and more.
Supabase MCP Server
by supabase-community
Enables AI assistants to interact directly with Supabase projects, allowing them to query databases, fetch configuration, manage tables, and perform other project‑level operations.
Azure
Officialby Azure
azure-mcp is a server that implements the Model Context Protocol (MCP) to connect AI agents with Azure services. It allows developers to interact with Azure resources like Storage, Cosmos DB, and the Azure CLI using natural language commands within their development environment.
Kubernetes
by Flux159
MCP Server for Kubernetes management commands, enabling interaction with Kubernetes clusters to manage pods, deployments, and services.
MCP K8S Go
by strowk
Provides a Golang‑based server that enables interaction with Kubernetes clusters via prompts, allowing listing of contexts, namespaces, resources, nodes, pods, events, logs, and executing commands inside pods.
ForeverVM
by jamsocket
Run arbitrary Python code securely in persistent, stateful sandboxes that remain available indefinitely.