DriftHound MCP Server
Enables Claude to discover and understand infrastructure-as-code drift by listing projects with drift, analyzing Terraform plan outputs, and providing remediation information.
README
DriftHound MCP Server
An MCP (Model Context Protocol) server that enables Claude to discover and understand IaC drift from DriftHound.
Features
- list_projects_with_drift - Find all projects that have drifting environments
- list_environments - List environments for a project with status filtering
- get_drift_details - Get full Terraform plan output for drift analysis
- get_environment_info - Get repository, branch, and directory for remediation
Installation
GitHub Packages (recommended)
The package is published to GitHub Packages. Because GitHub Packages requires authentication even for public packages, you need a GitHub personal access token with the read:packages scope.
- Add the following to your
~/.npmrc:
@drifthoundhq:registry=https://npm.pkg.github.com
//npm.pkg.github.com/:_authToken=YOUR_GITHUB_PAT
- Use
npxdirectly in your MCP client config — no global install needed (see below).
From source
npm install
npm run build
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
DRIFTHOUND_API_URL |
Yes | Base URL of your DriftHound instance |
DRIFTHOUND_API_TOKEN |
Yes | API token from DriftHound admin UI |
Claude Code Configuration
Add to your Claude Code settings (~/.claude/settings.json):
{
"mcpServers": {
"drifthound": {
"command": "npx",
"args": ["-y", "@drifthoundhq/mcp-server"],
"env": {
"DRIFTHOUND_API_URL": "https://drifthound.example.com",
"DRIFTHOUND_API_TOKEN": "your-api-token"
}
}
}
}
Claude Desktop Configuration
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"drifthound": {
"command": "npx",
"args": ["-y", "@drifthoundhq/mcp-server"],
"env": {
"DRIFTHOUND_API_URL": "https://drifthound.example.com",
"DRIFTHOUND_API_TOKEN": "your-api-token"
}
}
}
}
Usage
Once configured, Claude can use these tools to discover and understand drift:
Discover Drift
Claude, what projects have drift?
Claude will use list_projects_with_drift to find projects needing attention.
Investigate a Project
Show me the drifting environments in the EKS project
Claude will use list_environments with status=drift filter.
Analyze Drift Details
What's causing drift in eks/production?
Claude will use get_drift_details to get the full Terraform plan output.
Get Remediation Info
Where can I find the code to fix eks/production drift?
Claude will use get_environment_info to get the repository URL and directory.
Kubernetes Deployment
A Docker image is published to ghcr.io/drifthoundhq/mcp-server on every release. The server runs in HTTP mode when the PORT environment variable is set, exposing the MCP protocol at /mcp.
The quickest way to deploy on Kubernetes is via the Helm chart published to the OCI registry:
helm install drifthound oci://ghcr.io/drifthoundhq/charts/drifthound-mcp-server \
--namespace drifthound \
--create-namespace \
--set drifthoundApiUrl=https://your-drifthound.example.com \
--set drifthoundApiToken=your-api-token
Once running, point Claude Code at the in-cluster endpoint:
{
"mcpServers": {
"drifthound": {
"url": "http://drifthound-drifthound-mcp-server.drifthound.svc.cluster.local:3000/mcp"
}
}
}
See the Helm chart README for the full configuration reference, external secret support, and port-forward instructions for local access.
Development
# Run in development mode
npm run dev
# Build for production
npm run build
# Start production server
npm start
API Requirements
This MCP server requires DriftHound to have the read API endpoints enabled:
GET /api/v1/projects- List projectsGET /api/v1/projects/:key- Get project detailsGET /api/v1/projects/:key/environments- List environmentsGET /api/v1/projects/:key/environments/:key- Get environment detailsGET /api/v1/projects/:key/environments/:key/drift- Get latest drift check
License
MIT
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。