Sponsored by Deepsite.site

IaC Memory MCP Server

Created By
AgentWonga year ago
This is a personal project to determine whether or not Claude 3.5 Sonnet can write moderately complex MCP Server code (Python).
Content

IaC Memory MCP Server

A Model Context Protocol (MCP) server that enhances Claude AI's capabilities by providing persistent memory storage for Infrastructure-as-Code (IaC) components, with a focus on version tracking and relationship mapping for Terraform and Ansible resources.

NOTE

This was a personal project to determine the state of AI's ability if the person using it (me) doesn't have subject matter expertise (lack of Python knowledge). Since it has become rather cost prohibitive, I do not intend to develop or maintain this project further.

Overview

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

  • Persistent storage and version tracking for IaC components
  • Hierarchical resource organization with URI-based access
  • Comprehensive relationship mapping between components
  • Version-specific documentation management
  • Schema validation and temporal 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 general 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 for standardized 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 specialized prompts for IaC component discovery and analysis:

search_resources

  • Purpose: Search for IaC resources
  • Arguments:
    • provider: Provider name
    • resource_type: Resource type
  • Returns: Information about specific resources for the given provider

analyze_entity

  • Purpose: Analyze an entity and its relationships
  • Arguments:
    • entity_id: Entity ID
    • include_relationships: Include relationships
  • Returns: Detailed entity analysis including name, type, and observations

terraform_provider

  • Purpose: Get information about a Terraform provider
  • Arguments:
    • provider_name: Name of the Terraform provider (required)
    • version: Specific version to query (optional)
  • Returns: Detailed provider information for the specified version

ansible_module

  • Purpose: Get information about an Ansible module
  • Arguments:
    • collection_name: Name of the Ansible collection (required)
    • module_name: Name of the module (required)
    • version: Specific version to query (optional)
  • Returns: Detailed module information for the specified version

Tools

The server implements comprehensive tooling for IaC component management:

Terraform Tools

  • get_terraform_provider_info: Retrieve detailed provider information including version and resources
  • list_provider_resources: List all resources available for a specific provider
  • get_terraform_resource_info: Get detailed information about a specific resource type
  • add_terraform_provider: Register new providers with versioning
  • add_terraform_resource: Add resource definitions with schemas
  • update_provider_version: Update provider versions with new documentation

Ansible Tools

  • get_ansible_collection_info: Get detailed information about an Ansible collection
  • list_ansible_collections: List all available Ansible collections
  • get_collection_version_history: View version history of a collection
  • get_ansible_module_info: Get detailed information about a specific module
  • list_collection_modules: List all modules in a collection
  • get_module_version_compatibility: Check version compatibility of modules
  • add_ansible_collection: Register new Ansible collections
  • add_ansible_module: Add new modules with validation and documentation

Entity Operations

  • create_entity: Create new infrastructure entities
  • update_entity: Modify existing entity configurations
  • delete_entity: Remove entities with relationship cleanup
  • view_relationships: Analyze entity dependencies and relationships

Configuration

The server supports configuration through environment variables:

  • DATABASE_URL: SQLite database location
  • MCP_DEBUG: Enable debug logging when set
  • MCP_TEST_MODE: Enable test mode for database resets

For development, create a .env file:

DATABASE_URL=sqlite:////path/to/db.sqlite
MCP_DEBUG=1
MCP_TEST_MODE=1

Integration with Claude Desktop

Development Setup

"mcpServers": {
  "iac-memory": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/iac-memory-mcp-server",
      "run",
      "iac-memory-mcp-server"
    ]
    "env": {
          "DATABASE_URL": "sqlite:////home/herman/iac.db"
      }
  }
}

Production Setup

"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

# Development server with MCP Inspector
npx @modelcontextprotocol/inspector uv run iac-memory-mcp-server

License

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

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Tavily Mcp
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
DeepChatYour AI Partner on Desktop
ChatWiseThe second fastest AI chatbot™
Amap Maps高德地图官方 MCP Server
Playwright McpPlaywright MCP server
CursorThe AI Code Editor
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Serper MCP ServerA Serper MCP Server
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
WindsurfThe new purpose-built IDE to harness magic