Iac Memory MCP Server

🚀 Infrastructure as Code Memory MCP Server

An MCP (Model Context Protocol) server that enhances Claude AI's capabilities by providing persistent memory storage for IaC (Infrastructure as Code) components, enabling version tracking and relationship mapping. It primarily focuses on Terraform and Ansible resources.

⚠️ Important Note

This is a personal project aimed at testing the capabilities of AI when the user (me) lacks relevant professional knowledge. Due to the high cost, I do not plan to further develop or maintain this project.

📚 Overview

The IaC Memory MCP Server addresses the challenge of maintaining an accurate, version-aware context for IaC components by offering the following features:

• Persistent storage and version tracking for IaC components
• Hierarchical resource organization and URI-based access
• Comprehensive relationship mapping between components
• Version-specific document management
• Schema validation and time metadata tracking
• Automated relationship analysis and insights

✨ Core Components

🗂️ Resource Management

The server implements a sophisticated resource management system with hierarchical URIs:

Resource URI Structure

resources://<platform>/<category>/<name>

Supported platforms:

• terraform
• ansible
• iac (for generic infrastructure entities)

Example URIs:

resources://terraform/providers/aws
resources://terraform/resources/aws/s3_bucket
resources://ansible/collections/community.aws
resources://ansible/modules/community.aws/s3_bucket

Resource Templates

The server provides dynamic resource templates to standardize common access patterns:

• Terraform provider information: resources://terraform/providers/{provider_name}
• Resource type details: resources://terraform/resources/{provider_name}/{resource_type}
• Ansible collection data: resources://ansible/collections/{collection_name}
• Module information: resources://ansible/modules/{collection_name}/{module_name}

💬 Prompts

The server implements four prompts specifically for IaC component discovery and analysis:

search_resources

• Purpose: Search for IaC resources
• Parameters:
  • provider: Provider name
  • resource_type: Resource type
• Output: Returns a list of all resources for the specified platform

get_resource_schema

• Purpose: Get the schema for a specific resource
• Parameters:
  • platform: Platform name (terraform or ansible)
  • provider: Provider name
  • resource_type: Resource type
• Output: Returns detailed schema information for the resource

validate_resource

• Purpose: Validate the configuration of a resource
• Parameters:
  • platform: Platform name (terraform or ansible)
  • provider: Provider name
  • resource_type: Resource type
  • schema_version: Schema version
  • configuration: Configuration content to be validated
• Output: Returns validation results and error information

get_resource_relations

• Purpose: Get the relationship mapping between resources
• Parameters:
  • platform: Platform name (terraform or ansible)
  • provider: Provider name
  • resource_type: Resource type
• Output: Returns a list of relationships with other resources

🛠️ Tools

The server implements the following tools:

Terraform Tools

def get_terraform_provider_schemas():
    pass

def get_terraform_resource_schema(provider: str, resource_type: str) -> dict:
    pass

def validate_terraform_resource(
    provider: str,
    resource_type: str,
    schema_version: str,
    configuration: dict
) -> dict:
    pass

Ansible Tools

def get_ansible_collection_schemas():
    pass

def get_ansible_resource_schema(collection: str, resource_type: str) -> dict:
    pass

def validate_ansible_resource(
    collection: str,
    resource_type: str,
    schema_version: str,
    configuration: dict
) -> dict:
    pass

Entity Operation Tools

def get_entity_relationships() -> list:
    pass

⚙️ Configuration

Configure the server via environment variables:

DATABASE_URL=sqlite:////home/herman/iac.db

🔌 Integration with Claude Desktop

Development Environment

Add the following to uv.json to configure the development environment:

"mcpServers": {
    "iac-memory": {
        "command": "uv sync",
        "args": [],
        "env": {
            "DATABASE_URL": "sqlite:////home/herman/iac.db"
        }
    }
}

Production Environment

Add the following to uv.json to configure the production environment:

"mcpServers": {
    "iac-memory": {
        "command": "uvx",
        "args": [
            "--from",
            "git+https://github.com/AgentWong/iac-memory-mcp-server.git",
            "python",
            "-m",
            "iac_memory_mcp_server"
        ],
        "env": {
            "DATABASE_URL": "sqlite:////home/herman/iac.db"
        }
    }
}

💻 Development

Local Development

# Install dependencies
uv sync

# Run tests
uv run pytest

# Use the MCP inspector for the development server
npx @modelcontextprotocol/inspector uv run iac-memory-mcp-server

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.