R Huijts Portkey Admin MCP Server

🚀 Portkey MCP Server

Transform your AI assistant into a Portkey platform expert! This MCP server connects Claude and Portkey's APIs, enabling comprehensive management of AI configurations, workspaces, analytics, and user access.

🚀 Quick Start

📦 Installation

Install from Source

1. Clone this repository.
2. Install dependencies:

npm install

3. Copy the example environment file:

cp .env.example .env

4. Add your Portkey API key to the .env file:

PORTKEY_API_KEY=your_portkey_api_key_here

5. Then update your Claude configuration file:

{
  "mcpServers": {
    "portkey-server": {
      "command": "node",
      "args": [
        "/path/to/portkey-server/build/index.js"
      ],
      "env": {
        "PORTKEY_API_KEY": "your_portkey_api_key_here"
      }
    }
  }
}

Please ensure:

• Replace /path/to/portkey-server with your actual installation path.
• Add your Portkey API key in the env section.

After updating the configuration, restart Claude Desktop for the changes to take effect.

Install via Smithery

To automatically install the Portkey MCP server via Smithery:

npx -y @smithery/cli install @r-huijts/portkey-admin-mcp-server --client claude

💻 Usage Examples

Here are some real - world application scenarios:

• "What are the current API usage statistics across different models?"
• "Show the performance metrics of AI deployments."
• "Create a new workspace for my team project."
• "What is my current API key usage and remaining quota?"
• "Generate an analysis report of API calls from last month."
• "Set rate limits for the development environment."
• "Configure the fallback behavior for production endpoints."
• "Add team members to my Portkey workspace."
• "Show the latency statistics of API calls."
• "Set custom headers for API requests."

🔧 Technical Details

Environment Variables

✨ Features

This MCP server provides comprehensive access to the Portkey platform through the following features:

User and Access Management

• User Management: List and manage all users in your organization.
• User Invitation: Invite new users and customize roles and permissions.
• Workspace Access: Configure users' workspace access rights.
• Alternative Login: Support alternative login methods.

Analytics Reports

• Usage Statistics: Generate detailed statistics on API usage.
• Performance Monitoring: Monitor the performance of models and services.
• Logging: Record logs of all API calls.
• Usage Alerts: Set up notifications when thresholds are exceeded.

Workspace Management

• Multi - Tenant Support: Create and manage multiple independent workspaces.
• Resource Allocation: Configure resource usage limits for different workspaces.
• Access Control: Set workspace - level permission policies.
• Data Isolation: Implement data isolation between workspaces.

Configuration and API Settings

• Service Integration: Integrate with other cloud services and tools.
• Custom Rules: Define business rules to meet your needs.
• Monitoring Alerts: Configure alerts for performance and usage.
• Scalability: Support future feature expansion and service upgrades.

📄 License

MIT License

By installing the Portkey MCP server, you can easily achieve comprehensive management of AI configurations, user access, and workspaces, enhancing your work efficiency and performance.