OCI MCP Server
Enables interaction with Oracle Cloud Infrastructure services through a unified interface. Supports comprehensive OCI resource management including compute instances, storage, networking, databases, and monitoring through natural language commands in VS Code.
README
Oracle Cloud Infrastructure (OCI) MCP Server
A Model Context Protocol (MCP) server that provides access to Oracle Cloud Infrastructure services through a unified interface, optimized for VS Code integration.
Features
🚀 Unified OCI Management Tool
oci-manage - Comprehensive OCI resource management
- Compute: Instances, volumes, shapes, images
- Storage: Object storage buckets and objects
- Network: VCNs, subnets, security lists, gateways
- Database: DB systems, autonomous databases, backups
- Monitoring: Alarms, metrics, logs
- Identity: Users, groups, policies
Quick Start
1. Installation
git clone https://github.com/GoCoder7/oci-mcp-server.git
cd oci-mcp-server
npm install
2. Build
npm run build
3. Configure OCI Authentication
Copy the example environment file and configure your OCI credentials:
cp .env.example .env
Edit .env with your OCI credentials:
OCI_TENANCY_ID=ocid1.tenancy.oc1..aaaaaaaa...
OCI_USER_ID=ocid1.user.oc1..aaaaaaaa...
OCI_KEY_FINGERPRINT=aa:bb:cc:dd:ee:ff:gg:hh:ii:jj:kk:ll:mm:nn:oo:pp
OCI_PRIVATE_KEY_PATH=/path/to/your/oci_api_key.pem
OCI_REGION=us-ashburn-1
OCI_COMPARTMENT_ID=ocid1.compartment.oc1..aaaaaaaa... (optional)
4. VS Code Integration
Add to your VS Code settings.json:
{
"mcp.servers": {
"oci-mcp-server": {
"command": "node",
"args": ["/path/to/oci-mcp-server/dist/simple-index.js"],
"env": {
"OCI_TENANCY_ID": "your-tenancy-id",
"OCI_USER_ID": "your-user-id",
"OCI_KEY_FINGERPRINT": "your-key-fingerprint",
"OCI_PRIVATE_KEY_PATH": "/path/to/your/oci_api_key.pem",
"OCI_REGION": "us-ashburn-1"
}
}
}
}
Usage Examples
List Compute Instances
{
"service": "compute",
"action": "list",
"resourceType": "instances",
"compartmentId": "ocid1.compartment.oc1..aaaaaaaa..."
}
Get Specific Instance Details
{
"service": "compute",
"action": "get",
"resourceType": "instance",
"resourceId": "ocid1.instance.oc1.iad.aaaaaaaa..."
}
Create Object Storage Bucket
{
"service": "storage",
"action": "create",
"resourceType": "bucket",
"parameters": {
"name": "my-new-bucket",
"compartmentId": "ocid1.compartment.oc1..aaaaaaaa..."
}
}
List VCNs
{
"service": "network",
"action": "list",
"resourceType": "vcns",
"compartmentId": "ocid1.compartment.oc1..aaaaaaaa..."
}
Monitor Database Performance
{
"service": "monitoring",
"action": "list",
"resourceType": "metrics",
"parameters": {
"namespace": "oci_autonomous_database"
}
}
OCI Authentication Setup
1. Create API Key Pair
- Log into OCI Console
- Go to Profile → User Settings → API Keys
- Click "Add API Key"
- Generate or upload a key pair
- Save the private key file securely
2. Required Information
- Tenancy OCID: Found in Profile → Tenancy
- User OCID: Found in Profile → User Settings
- Key Fingerprint: Generated when creating API key
- Private Key Path: Location of your .pem file
- Region: Your preferred OCI region
- Compartment OCID: Optional default compartment
3. Set File Permissions
chmod 600 /path/to/your/oci_api_key.pem
Available Services & Actions
Services
compute- Compute instances and volumesstorage- Object storage buckets and objectsnetwork- VCNs, subnets, securitydatabase- Database systems and autonomous DBsmonitoring- Alarms, metrics, loggingidentity- Users, groups, policies
Actions
list- List resources of specified typeget- Get details of specific resourcecreate- Create new resourceupdate- Update existing resource (where supported)delete- Delete resource (where supported)start- Start resource (instances, databases)stop- Stop resource (instances, databases)
Resource Types
Compute: instances, volumes, images, shapes
Storage: buckets, objects
Network: vcns, subnets, security-lists, gateways
Database: db-systems, autonomous-databases, backups
Monitoring: alarms, metrics, logs
Identity: users, groups, policies
Development
Project Structure
src/
├── simple-index.ts # Main MCP server (simplified)
├── index.ts # Full MCP server (advanced)
├── types/
│ └── oci.ts # Type definitions
├── utils/
│ └── oci-client.ts # OCI client management
└── tools/
├── compute.ts # Compute management
├── storage-network.ts # Storage & network
├── database-analytics.ts # Database & analytics
└── monitoring-security.ts # Monitoring & security
Available Scripts
npm run build- Build the projectnpm run dev- Run in development modenpm run watch- Run with auto-reloadnpm start- Run compiled version
Current Implementation
The server currently provides:
- ✅ MCP protocol integration
- ✅ OCI credential validation
- ✅ VS Code tool interface
- ✅ Basic service structure
- 🚧 Full OCI SDK integration (in progress)
Troubleshooting
Common Issues
Authentication Errors
- Verify OCI credentials are correct
- Check private key file permissions (600)
- Ensure user has proper IAM policies
Connection Issues
- Verify region is correct
- Check network connectivity to OCI
- Validate compartment access
VS Code Integration
- Ensure MCP extension is installed
- Check server configuration in settings.json
- Verify file paths are absolute
Error Messages
"OCI credentials not configured"
- Set required environment variables
- Check .env file or VS Code settings
"Cannot use import statement outside a module"
- Ensure package.json has
"type": "module" - Verify build completed successfully
Contributing
- Fork the repository
- Create feature branch
- Make changes
- Add tests if applicable
- Submit pull request
Security
- Never commit
.envfiles or private keys - Use IAM policies to limit permissions
- Regularly rotate API keys
- Monitor OCI usage and costs
License
MIT License - see LICENSE file for details
Support
For issues:
- Check troubleshooting section
- Review OCI documentation
- Open GitHub issue
- Consult OCI community forums
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。