portkey-mcp-server
About
This server bridges AI tools and services to Portkey through the Model Context Protocol (MCP). It is for developers who need to manage Portkey prompts—create, list, and render them—from MCP‑compatible clients like Cursor IDE and Claude Desktop.
Details
- Author
- rvoh-emccaleb
- Downloads
- 294
- Categories
- Other
Jump to
- Exposes three Portkey prompt tools via MCP
- Supports stdio and SSE transport modes
- Works with Cursor IDE and Claude Desktop
- Ready‑to‑use Docker image on Docker Hub
- Can run as a standalone Go binary
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
portkey-mcp-serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via Docker (docker run ericmccaleb/portkey-mcp-server:latest), a pre‑built binary (make build), or from source (go run). Set the required environment variable PORTKEY_API_KEY and optionally configure transport (TRANSPORT=stdio or TRANSPORT=sse) and the SSE address (TRANSPORT_SSE_ADDRESS). Then connect using the MCP client configuration (e.g., .cursor/mcp.json or claude_desktop_config.json).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"portkey-mcp-server": {
"portkey-mcp-server": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"\\"
]
}
}
}
}McpServers
{
"portkey-mcp-server": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"\\"
]
}
}portkey-mcp-server
A Model Context Protocol (MCP) server implementation for Portkey. This application serves as a bridge for connecting various AI tools and services to Portkey through the Model Context Protocol.
Table of Contents
- Supported MCP Features - Tools - Installation - Docker - Binary - From Source - Configuration - Usage - With Cursor IDE - With Claude Desktop - Manual SSE Requests - Contributing - LicenseSupported MCP Features
Tools
-prompt_create
- prompt_render
- prompts_list
Installation
Quick Start: For immediate integration with AI tools, jump directly to the Cursor IDE or Claude Desktop usage sections. These provide ready-to-use setup instructions for each tool.
Docker
The easiest way to get started is with the pre-built Docker image from Docker Hub:
```shell
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
