Terraform Registry MCP Server
Enables AI assistants to search and retrieve information about Terraform providers and modules from the public Terraform registry, including detailed documentation, version information, and resource specifications.
README
Terraform Registry MCP Server
A Model Context Protocol (MCP) server that provides comprehensive access to the Terraform public registry. This server enables AI assistants to search and retrieve information about Terraform providers, modules, and documentation.
Features
Module Tools
- 🔍 search_modules - Search for Terraform modules by name or keywords
- 📦 get_module_details - Get detailed information about a specific module
- 🏷️ get_latest_module_version - Get the latest version of a module
- 📋 list_module_versions - List all available versions of a module
Provider Tools
- 🔍 search_providers - Search for Terraform providers
- 📦 get_provider_details - Get detailed information about a provider
- 🏷️ get_latest_provider_version - Get the latest version of a provider
- 📋 list_provider_versions - List all available versions of a provider
- 📚 get_provider_docs - Fetch full provider documentation (setup, auth, version notes)
- 📄 get_provider_resource_docs - Fetch complete resource docs (args, attributes, examples)
- 📄 get_provider_data_source_docs - Fetch complete data source docs
- 🔎 search_provider_docs - Search within provider documentation for specific errors, topics, or troubleshooting
New! Documentation tools now fetch the actual markdown content from the registry, including version-specific information, breaking changes, upgrade guides, and complete argument/attribute references.
Installation
Using Docker (Recommended)
Build and run with Docker Compose:
docker-compose up -d
Or build manually:
docker build -t terraform-registry-mcp-server .
docker run -d -p 3002:3002 --name terraform-registry-mcp-server \
-e TRANSPORT_MODE=http \
-e PORT=3002 \
terraform-registry-mcp-server
Local Development
Install dependencies:
pip install -e .
Run in stdio mode (for local MCP clients):
terraform-mcp-server
Run in HTTP mode:
export TRANSPORT_MODE=http
export PORT=3002
terraform-mcp-server
Configuration
Environment Variables
TRANSPORT_MODE- Transport mode:stdio(default) orhttpPORT- HTTP server port (default: 3002)
VS Code MCP Configuration
Add to your VS Code mcp.json:
{
"mcpServers": {
"terraform": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"terraform-mcp-server"
]
}
}
}
Or for HTTP transport:
{
"mcpServers": {
"terraform": {
"url": "http://localhost:3002/mcp"
}
}
}
Usage Examples
Search for AWS VPC modules
search_modules(query="vpc", provider="aws", limit=10)
Get module details
get_module_details(
namespace="terraform-aws-modules",
name="vpc",
provider="aws"
)
Search for providers
search_providers(query="azure", tier="official")
Get latest provider version
get_latest_provider_version(namespace="hashicorp", name="aws")
Get provider documentation
# Get full provider overview with version info and breaking changes
get_provider_docs(namespace="hashicorp", name="azurerm")
# Get specific version documentation (useful for compatibility checks)
get_provider_docs(namespace="hashicorp", name="azurerm", version="3.0.0")
Get specific resource documentation
# Fetches complete documentation including all arguments and attributes
get_provider_resource_docs(
namespace="hashicorp",
name="aws",
resource_name="aws_instance"
)
# Check a specific version's resource documentation
get_provider_resource_docs(
namespace="hashicorp",
name="azurerm",
resource_name="azurerm_virtual_machine",
version="3.85.0"
)
Get data source documentation
get_provider_data_source_docs(
namespace="hashicorp",
name="aws",
data_source_name="aws_ami"
)
Deployment to Azure Container Apps
This server is designed for easy deployment to Azure Container Apps:
- Build and push to Azure Container Registry:
az acr build --registry <your-acr> --image terraform-mcp-server:latest .
- Deploy to Container Apps:
az containerapp create \
--name terraform-mcp-server \
--resource-group <your-rg> \
--environment <your-env> \
--image <your-acr>.azurecr.io/terraform-mcp-server:latest \
--target-port 3002 \
--ingress external \
--env-vars TRANSPORT_MODE=http PORT=3002
Architecture
- FastMCP - Uses the official MCP Python SDK with FastMCP for simplified server creation
- StreamableHTTP Transport - Supports modern HTTP transport for cloud deployment
- Public Registry Only - Focuses on public Terraform registry (no authentication required)
- Lightweight - Minimal dependencies, fast startup
Comparison with HashiCorp's Server
This is a simplified version compared to HashiCorp's official terraform-mcp-server:
Included:
- ✅ Public registry search (modules & providers)
- ✅ Module and provider details
- ✅ Version management
- ✅ HTTP transport for cloud deployment
- ✅ Docker support
Not Included:
- ❌ HCP Terraform / Terraform Enterprise integration
- ❌ Workspace management
- ❌ Run execution
- ❌ Variable management
- ❌ Private registry access
License
MIT License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
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。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。