This MCP server provides tools to interact with the AWS Programmatic Service Reference, allowing you to:
# Create and activate a virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate # On Unix/macOS
.venv\Scripts\activate # On Windows
# Install dependencies
pip install -r requirements.txt
You can run the server directly:
python aws_service_reference.py
Open your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
Add the server configuration:
{
"mcpServers": {
"aws-service-reference": {
"command": "python",
"args": ["/ABSOLUTE/PATH/TO/aws_service_reference.py"]
}
}
}
Replace /ABSOLUTE/PATH/TO/
with the actual path to where you saved the server file.
The server provides four tools:
list_aws_services
: Lists all available AWS servicesget_service_actions
: Gets API actions for a specific AWS serviceget_action_condition_keys
: Gets condition keys supported by a specific API actionget_action_resource_types
: Gets resource types supported by a specific API actionOnce connected, you can ask Claude questions like:
You can test the server using the MCP Inspector:
mcp dev aws_service_reference.py
The project uses the following dependencies (specified in requirements.txt
):
mcp[cli]>=0.1.0
: The Model Context Protocol SDK with CLI toolshttpx>=0.26.0
: Modern HTTP client for making API requestsIf you encounter issues:
pip install -r requirements.txt
~/Library/Logs/Claude/mcp*.log
%APPDATA%\Claude\logs\mcp*.log
This project is licensed under the MIT License.
{
"mcpServers": {
"aws-service-reference": {
"env": {},
"args": [
"/ABSOLUTE/PATH/TO/aws_service_reference.py"
],
"command": "python"
}
}
}
Seamless access to top MCP servers powering the future of AI integration.