Descope MCP Server

What does “Descope” MCP Server do?

The Descope MCP (Model Context Protocol) Server provides an interface to interact with Descope’s Management APIs, enabling AI assistants and development tools to search and retrieve project-related information from Descope. By bridging external data sources (Descope Management APIs) with AI workflows, it allows users to perform tasks such as searching audit logs, managing users, and handling project data directly from their preferred AI development environment. This integration streamlines developer productivity by automating repetitive management actions and surfacing key project insights, making it easier to build, maintain, and monitor secure authentication experiences in modern applications.

List of Prompts

No information found about prompt templates in the provided repository.

List of Resources

No explicit resources section found in the repository or documentation.

List of Tools

• search-audits: Retrieves up to 10 audit log entries from your Descope project.
• search-users: Retrieves up to 10 user records from your Descope project.
• create-user: Creates a new user in your Descope project.
• invite-user: Invites a new user to your Descope project.

Use Cases of this MCP Server

• Audit Log Retrieval: Developers and security teams can quickly access the latest audit log entries to monitor activity and troubleshoot issues.
• User Search: Enables support teams or automated agents to search and retrieve user information for account management or customer support workflows.
• Automated User Creation: Allows onboarding scripts or automated flows to create new users in Descope projects without manual intervention.
• User Invitation Workflow: Streamlines the process of inviting new users to projects, enabling seamless collaboration or customer onboarding.
• Project Insights and Monitoring: Facilitates integration with dashboards or monitoring tools to keep track of project events and user activities.

How to set it up

Windsurf

No specific setup instructions for Windsurf provided in the repository.

Claude

1. Prerequisites: Ensure you have Node.js (18+), Claude Desktop installed, and valid Descope Project ID and Management Key.
2. Installation:

   npx -y @smithery/cli install @descope-sample-apps/descope-mcp-server --client claude
   

3. Configuration:
   • Open Claude Desktop, enable Developer Mode, and edit claude_desktop_config.json.
   • On macOS:

     code ~/Library/Application\ Support/Claude/claude_desktop_config.json
     

   • On Windows:

     code %APPDATA%\Claude\claude_desktop_config.json
     

4. Add the Descope MCP server:

   {
     "mcpServers": {
       "descope": {
         "command": "npx",
         "args": [
           "-y",
           "@descope-sample-apps/descope-mcp-server@latest"
         ],
         "env": {
           "DESCOPE_PROJECT_ID": "your-project-id",
           "DESCOPE_MANAGEMENT_KEY": "your-management-key"
         }
       }
     }
   }
   

5. Save and Restart: Save the configuration file and restart Claude Desktop to activate the MCP server.

Cursor

No specific setup instructions for Cursor provided in the repository.

Cline

No specific setup instructions for Cline provided in the repository.

Securing API Keys Example

Use environment variables in your configuration to secure API keys:

{
  "mcpServers": {
    "descope": {
      "command": "npx",
      "args": [
        "-y",
        "@descope-sample-apps/descope-mcp-server@latest"
      ],
      "env": {
        "DESCOPE_PROJECT_ID": "your-project-id",
        "DESCOPE_MANAGEMENT_KEY": "your-management-key"
      },
      "inputs": {}
    }
  }
}

Note: Replace "your-project-id" and "your-management-key" with your actual credentials and do not hardcode sensitive values in public configurations.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "descope": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change "descope" to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Roots Support | ⛔ | No mention of Roots support |

Based on the above, the Descope MCP Server is a focused, practical integration for Descope Management APIs, with clear tool support and easy setup for Claude, but lacks advanced MCP features like prompts, resources, roots, and sampling.

Our opinion

This MCP server is practical and production-ready for projects using Descope, with a straightforward set of tools and good documentation for setup on Claude Desktop. However, the absence of prompt templates, resources, roots, and sampling support limits its versatility for broader MCP use cases. Overall, it provides value for its intended audience but is less suitable for advanced or highly customizable MCP workflows.

MCP Score