sceptre-mcp-server

A Model Context Protocol (MCP) server that exposes Sceptre CloudFormation management operations as tools for AI agents.

What it does

AI agents (Claude, Kiro, etc.) can connect to this server and manage AWS CloudFormation stacks through Sceptre's Python API. The server exposes 22 tools covering the full stack lifecycle:

• Stack lifecycle — create, update, delete, launch
• Querying — status, describe, outputs, resources, events
• Templates — generate, validate
• Diff & drift — diff against deployed state, detect and show drift
• Change sets — create, describe, list, execute, delete
• Discovery — list stacks, dump resolved config

Requirements

• Python 3.10+
• A configured Sceptre project with config/ and templates/ directories

Installation

pip install sceptre-mcp-server

Or run directly without installing:

uvx sceptre-mcp-server

MCP Client Configuration

Kiro

Add to .kiro/settings/mcp.json:

{
  "mcpServers": {
    "sceptre": {
      "command": "uvx",
      "args": ["sceptre-mcp-server"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "sceptre": {
      "command": "uvx",
      "args": ["sceptre-mcp-server"]
    }
  }
}

Tools Reference

Every tool requires a sceptre_project_dir parameter pointing to your Sceptre project root. Stack-specific tools also require a stack_path relative to the config/ directory.

Stack Lifecycle

Querying

Templates

Diff & Drift

Change Sets

Discovery & Configuration

Example Usage

Once connected, an AI agent can invoke tools like:

> List all stacks in my project at /home/user/infra

Calls: list_stacks(sceptre_project_dir="/home/user/infra")

> What's the status of the dev VPC stack?

Calls: get_stack_status(sceptre_project_dir="/home/user/infra", stack_path="dev/vpc.yaml")

> Show me what would change if I deploy the prod API stack

Calls: diff_stack(sceptre_project_dir="/home/user/infra", stack_path="prod/api.yaml")

AWS Configuration

Sceptre uses the standard AWS credential chain. To specify a profile or region, pass environment variables through your MCP client config:

{
  "mcpServers": {
    "sceptre": {
      "command": "uvx",
      "args": ["sceptre-mcp-server"],
      "env": {
        "AWS_PROFILE": "my-profile",
        "AWS_DEFAULT_REGION": "us-west-2"
      }
    }
  }
}

Contributing

See CONTRIBUTING.md for development setup, testing, pre-commit hooks, and type checking.

License

Apache-2.0