Portkey

Provides centralized Portkey platform management via MCP for workspaces, analytics, and user access.
  • javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You set up the Portkey MCP Server to manage Portkey configurations, workspaces, analytics, and user access from a centralized client. This server bridges your Portkey platform with MCP-capable clients, enabling streamlined administration and reporting across your organization.

How to use

Connect your MCP client to the Portkey MCP Server to access comprehensive management features. Use the Portkey MCP Server to list users, invite new members, assign roles, view workspace details, monitor API usage and costs, manage virtual keys, and generate analytics reports. You can configure access per workspace and organization, then run actions such as creating workspaces, inviting members, reviewing configurations, and extracting usage metrics. All actions are available through the MCP client’s interface, which communicates with the Portkey MCP Server to perform operations and return results.

How to install

Prerequisites you need before installation: Node.js (including npm) must be installed on your system.

From source, follow these steps to install and configure the Portkey MCP Server on your machine.

From source install steps

# 1) Clone the repository
git clone https://example.com/portkey-admin-mcp-server.git

# 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
# Edit the file to include your API key, for example:
# PORTKEY_API_KEY=your_portkey_api_key_here
{
  "mcpServers": {
    "portkey-server": {
      "command": "node",
      "args": [
        "/path/to/portkey-server/build/index.js"
      ],
      "env": {
        "PORTKEY_API_KEY": "your_portkey_api_key_here"
      }
    }
  }
}
  1. Update your Claude configuration by replacing "/path/to/portkey-server" with the actual installation path and ensuring the Portkey API key is set in the environment block. Then restart the Claude Desktop client for changes to take effect.

Installing via Smithery

Install Portkey MCP Server for Claude Desktop automatically via Smithery using the following command.

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

Additional setup notes

Environment variable for the server is PORTKEY_API_KEY. This value must be available to the MCP server process so that all Portkey API interactions are authenticated. Ensure you keep this key secure and do not share it publicly.

Notes on usage with MCP clients

When you start the Portkey MCP Server, your MCP client should be able to list users, manage workspaces, view analytics, and configure access rules. Use the client’s UI to perform actions such as inviting users, assigning roles, reviewing workspace configurations, generating reports, and monitoring API usage and key usage across your organization.

Troubleshooting checklist

  • Verify that PORTKEY_API_KEY is set in the environment where the MCP server runs.

  • Ensure the server process is running and reachable by your MCP client.

  • Check that the path to the server script (build/index.js) is correct in your mcpServers configuration.

Security considerations

Treat the Portkey API key as a secret. Use least-privilege access where possible and rotate the key periodically. Restrict client access to trusted networks and monitor for unusual activity in your Portkey workspace and analytics dashboards.

License

ISC License - see the license terms for details.

Available tools

list_users

List all users in your Portkey organization

invite_user

Invite new users with customizable roles and permissions

workspace_overview

List and view detailed information about all workspaces

usage_analytics

Track detailed user activity and request patterns

cost_analysis

Monitor and analyze costs across different time periods

virtual_key_management

Monitor and manage API keys with usage limits and rate limits

config_listings

View all available configurations in your organization

api_settings

Track API endpoints and their configurations

reports

Generate analytics reports for selected time ranges

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational