Portkey MCP Server
Connects Claude to Portkey's API for managing AI configurations, workspaces, analytics, and user access, providing comprehensive control over API usage and settings.
r-huijts
Tools
list_all_users
List all users in your Portkey organization, including their roles and account details
invite_user
Invite a new user to your Portkey organization with specific workspace access and API key permissions
get_user_stats
Retrieve detailed analytics data about user activity within a specified time range, including request counts and costs
list_workspaces
Retrieve all workspaces in your Portkey organization, including their configurations and metadata
get_workspace
Retrieve detailed information about a specific workspace, including its configuration, metadata, and user access details
list_configs
Retrieve all configurations in your Portkey organization, including their status and workspace associations
list_virtual_keys
Retrieve all virtual keys in your Portkey organization, including their usage limits, rate limits, and status
get_cost_analytics
Retrieve detailed cost analytics data over time, including total costs and averages per request
get_config
Retrieve detailed information about a specific configuration, including cache settings, retry policies, and routing strategy
README
Portkey MCP Server
Transform your AI assistant into a Portkey platform expert! This MCP server connects Claude to Portkey's API, enabling comprehensive management of AI configurations, workspaces, analytics, and user access.
<a href="https://glama.ai/mcp/servers/iftjfqrk0v"><img width="380" height="200" src="https://glama.ai/mcp/servers/iftjfqrk0v/badge" alt="Portkey Server MCP server" /></a>
Installation
From Source
- Clone this repository
- Install dependencies:
npm install
- Copy the example environment file:
cp .env.example .env
- Add your Portkey API key to the
.env
file:
PORTKEY_API_KEY=your_portkey_api_key_here
- 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"
}
}
}
}
Make sure to:
- Replace
/path/to/portkey-server
with the actual path to your installation - Add your Portkey API key in the
env
section
After updating the configuration, restart Claude Desktop for the changes to take effect.
Installing via Smithery
To install Portkey MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @r-huijts/portkey-admin-mcp-server --client claude
Real-World Use Cases
- "What are my current API usage statistics across different models?"
- "Show me the performance metrics for my AI deployments"
- "Create a new workspace for my team's project"
- "What's my current API key usage and remaining credits?"
- "Generate an analytics report for last month's API calls"
- "Set up rate limiting for my development environment"
- "Configure fallback behavior for my production endpoints"
- "Add team members to my Portkey workspace"
- "Show me the latency statistics for my API calls"
- "Set up custom headers for my API requests"
🔑 Environment Variables
Variable | Description |
---|---|
PORTKEY_API_KEY | Your Portkey API key (required) |
🌟 Features
This MCP server provides comprehensive access to Portkey's platform through the following capabilities:
User & Access Management
- User Administration: List and manage all users in your Portkey organization
- User Invitations: Invite new users with customizable roles and permissions
- Workspace Access: Configure user access levels across different workspaces
- Role-Based Control: Assign admin, manager, or member roles at organization and workspace levels
Analytics & Reporting
- Usage Analytics: Track detailed user activity and request patterns
- Cost Analysis: Monitor and analyze costs across different time periods
- Request Metrics: View request counts, token usage, and response times
- Filtered Reports: Generate reports based on custom criteria like status codes, virtual keys, and time ranges
Workspace Management
- Workspace Overview: List and view detailed information about all workspaces
- Configuration Management: Access and review workspace configurations
- Virtual Key Management: Monitor and manage API keys with usage limits and rate limits
- Workspace Settings: View and track workspace metadata and user associations
Configuration & API Settings
- Config Listings: View all available configurations in your organization
- Detailed Config Info: Access cache settings, retry policies, and routing strategies
- Virtual Key Details: Monitor key status, usage limits, and rate limits
- API Integration: Track API endpoints and their configurations
License
This project is licensed under the ISC License - see the LICENSE file for details
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Playwright MCP Server
Provides a server utilizing Model Context Protocol to enable human-like browser automation with Playwright, allowing control over browser actions such as navigation, element interaction, and scrolling.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Apple MCP Server
Enables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
contentful-mcp
Update, create, delete content, content-models and assets in your Contentful Space