AWS Service Reference MCP Server
@MitchyBAwesome
AWS Service Reference MCP Server について
An MCP Server for accessing the AWS Programatic Service Authorisation Reference
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"sar-mcp": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is AWS Service Reference MCP Server?
The AWS Service Reference MCP Server provides tools to query the AWS Programmatic Service Reference. It enables users to list AWS services, retrieve API actions for a service, and inspect condition keys, resource types, and action properties (e.g., whether an action is a write or list operation). It is aimed at developers and administrators working with AWS IAM policies or service documentation.
How to use AWS Service Reference MCP Server?
Install Python 3.10 or higher, clone the repository, and install dependencies with pip install -r requirements.txt. Run the server directly with python aws_service_reference.py. For use with Claude Desktop, add the server configuration to claude_desktop_config.json using an absolute path to aws_service_reference.py. Once connected, ask Claude natural language questions about AWS services and API actions.
Key features of AWS Service Reference MCP Server
- Lists all available AWS services
- Retrieves API actions for a specific service
- Gets condition keys supported by an API action
- Gets resource types supported by an API action
- Gets action properties (write, list, permission management, etc.)
Use cases of AWS Service Reference MCP Server
- Exploring which AWS services exist and their available API actions
- Checking condition keys and resource types for an IAM policy statement
- Distinguishing write operations from read-only operations when building policies
- Understanding permission management actions that require careful access control
- Identifying actions that only modify tags (tagging-only operations)
FAQ from AWS Service Reference MCP Server
What are the system requirements?
Python 3.10 or higher is required. A virtual environment is recommended.
How do I configure the server with Claude Desktop?
Add an entry to claude_desktop_config.json with "command": "python" and "args" containing the absolute path to aws_service_reference.py. The configuration file is located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS and %APPDATA%\Claude\claude_desktop_config.json on Windows.
What dependencies does the server require?
The project depends on mcp[cli]>=0.1.0 (MCP SDK with CLI tools) and httpx>=0.26.0 (HTTP client). These are listed in requirements.txt.
How can I troubleshoot connection issues?
Verify that Python 3.10+ is installed and all dependencies are installed (pip install -r requirements.txt). Check the Claude Desktop logs at ~/Library/Logs/Claude/mcp*.log (macOS) or %APPDATA%\Claude\logs\mcp*.log (Windows). Ensure the path in the configuration is absolute.
What tools does the server provide?
The server exposes five tools: list_aws_services, get_service_actions, get_action_condition_keys, get_action_resource_types, and get_action_properties.
「クラウドとインフラ」の他のコンテンツ
Run Model Context Protocol (MCP) servers with AWS Lambda
awslabsRun existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions
Azure DevOps MCP Server
Tiberriver256An MCP server for Azure DevOps
Terraform MCP Server
hashicorpThe Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
K8s MCP Server
alexei-ledK8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI syste
Lambda MCP Server Demo (Streamable HTTP)
mikegc-awsCreates a simple MCP tool server with "streaming" HTTP.
コメント