home / mcp / quicksight mcp mcp server

Quicksight MCP MCP Server

Provides an MCP-compliant endpoint for the Amazon QuickSight OpenAPI spec enabling context-aware RPC interactions.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "anhminhnguyen3110-quicksight-mcp": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{...}",
        "SECURITY": "{...}",
        "CONFIG_PATH": "path/to/mcp_config.json"
      }
    }
  }
}

An MCP Server lets you host a Model Context Protocol endpoint for a defined API, enabling clients to interact with the OpenAPI-based service in a structured, context-aware way. This server focuses on the Amazon QuickSight 2018-04-01 OpenAPI spec, making it easier to plug into MCP clients and enable standardized RPC-style communication.

How to use

You run the MCP server locally or in your environment and connect your MCP client to the server using the stdio transport by launching the server process. The server can be configured through environment variables to point to a JSON config and security settings. Once running, your client can invoke supported MCP methods that correspond to the underlying OpenAPI spec, enabling interactions with the QuickSight API in a consistent MCP-enabled workflow.

How to install

Ensure you have Python 3.9 or newer installed on your system
Install the required tooling: pip and uv (uv is used to run Python commands in some setups)
Clone the MCP server project to your workspace
Install development dependencies and set up the environment
Run the server in stdio mode to begin accepting MCP calls

# Prerequisites
# Ensure Python 3.9+ is installed on your system
python --version

# Install the project and dependencies (example commands; replace <repository-url> with the actual URL)
git clone <repository-url>
cd mcp-server

# Install development dependencies
pip install -e ".[dev]"
# Optional alternative using uv to run editable dependencies
uv pip install --editable ".[dev]"

# Start the MCP server in stdio mode
python mcp_server/main.py stdio

Configuration and security notes

Configure how the server loads its settings through environment variables. The following are supported:

- CONFIG_PATH: Path to a JSON configuration file (for example, mcp_server/mcp_config.json)

- CONFIG: A JSON string containing the server configuration

- SECURITY: Environment variables for security parameters (for example, API keys)

Available tools

ruff

Lints and formats the codebase to maintain code quality and consistency.

mypy

Performs static type checking to catch type errors early.

pytest

Runs unit tests to ensure functionality and regressions are caught.

pre-commit

Enforces code quality checks before commits via configured hooks.