Happy slice of mcp pizzaMCP.pizza

workos-mcp

MCP.Pizza Chef: ZukAi-MCP

workos-mcp is a lightweight MCP server deployed on Cloudflare Workers that enables Cursor Agents to interact seamlessly with the WorkOS API. It provides a structured interface for agents to access WorkOS functionalities, facilitating secure and efficient integration with identity and access management features. The server is easy to install, configure, and deploy, making it ideal for developers looking to extend their AI agents with WorkOS capabilities.

Use This MCP server To

Enable Cursor Agents to perform identity management via WorkOS API Integrate WorkOS authentication flows into AI agent workflows Automate user provisioning and directory synchronization Access WorkOS audit logs through AI-driven queries Manage SSO configurations programmatically via agents Deploy WorkOS API interactions on Cloudflare Workers for scalability

README

workos-mcp

This is a lightweight Model Control Protocol (MCP) server bootstrapped with create-mcp, and deployed on Cloudflare Workers.

This MCP Server allows agents (like Cursor Agents) to interact with the WorkOS API.

Available Tools

See src/index.ts for the current list of tools. Every method in the class is an MCP tool.

Installation

  1. Run the automated install script to clone this MCP server and deploy it to your Cloudflare account:
bun create mcp --clone https://github.com/zueai/workos-mcp

  1. Open Cursor Settings -> MCP -> Add new MCP server and paste the command that was copied to your clipboard.

  2. Upload your WorkOS API key and client ID as secrets:

bunx wrangler secret put WORKOS_API_KEY
bunx wrangler secret put WORKOS_CLIENT_ID

Deploying Changes

  1. Run the deploy script:
bun run deploy
  1. Then reload your Cursor window to use the updated tools.

How to create new MCP tools

To create new MCP tools, add methods to the MyWorker class in src/index.ts. Each function will automatically become an MCP tool that your agent can use.

Example:

/**
 * A warm, friendly greeting from your MCP server.
 * @param name {string} the name of the person we are greeting.
 * @return {string} the contents of our greeting.
 */
sayHello(name: string) {
    return `Hello from an MCP Worker, ${name}!`;
}

The JSDoc comments are important:

  • First line becomes the tool's description
  • @param tags define the tool's parameters with types and descriptions
  • @return tag specifies the return value and type

workos-mcp FAQ

How do I install the workos-mcp server?
Use the automated install script with bun create mcp to clone and deploy it to Cloudflare Workers, then configure it in Cursor Settings.
How do I provide authentication credentials to workos-mcp?
Upload your WorkOS API key and client ID as secrets using wrangler secret commands before deploying.
Can I deploy updates to workos-mcp easily?
Yes, run the provided deploy script and reload your Cursor window to apply changes.
What environment does workos-mcp run on?
It runs on Cloudflare Workers, providing a scalable and lightweight server environment.
How does workos-mcp expose WorkOS API methods?
Each method in the server's class is exposed as an MCP tool accessible by agents.
Is workos-mcp compatible with multiple AI agent platforms?
It is designed primarily for Cursor Agents but can be adapted for other MCP-compatible agents.
What security measures are recommended?
Store API keys and client IDs securely as secrets and restrict access to authorized agents only.
Where can I find the list of available tools?
The current tools are listed in the src/index.ts file of the repository.