mcpField
D
Descope MCP Server

Descope MCP Server

Local
github.com/descope-sample-appsSecurity38Updated 86w ago

About Descope MCP Server

The Descope MCP server provides access to Descope's Management APIs for searching audit logs and user records in a project. It is aimed at administrators who want to work with Descope projects from Claude Desktop.

Key features

  1. 01Retrieve audit log entries
  2. 02Search user records
  3. 03Create new users
  4. 04Invite users to the project

Use cases

  1. 01Reviewing recent audit log entries in Claude Desktop
  2. 02Looking up users in a Descope project
  3. 03Creating or inviting users through a conversation

MCP support

The server runs as an MCP server and exposes search-audits, search-users, create-user and invite-user tools to MCP clients, over stdio or SSE.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Descope MCP Server

smithery badge

Introduction

The Descope Model Context Protocol (MCP) server provides an interface to interact with Descope's Management APIs, enabling the search and retrieval of project-related information.

Available 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.

Requirements

Before proceeding, make sure you have the following:

To confirm your Node.js installation, run:

node --version  # Expected output: v18.0.0 or later

Setup Instructions

Installing via Smithery

To install Descope MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @descope-sample-apps/descope-mcp-server --client claude
Manual Installation
  1. Clone the repository:

    git clone https://github.com/descope-sample-apps/descope-mcp-server.git
    cd descope-mcp-server
    
  2. Install the necessary dependencies:

    npm install
    
  3. Build the project:

    npm run build
    

Configuration

1. Configure Claude Desktop to recognize the Descope MCP server

To locate the claude_desktop_config.json file, open the Claude Desktop app and enable Developer Mode from the top-left menu bar.

Once enabled, go to Settings (also in the top-left menu), navigate to the Developer section, and click the Edit Config button to access and edit claude_desktop_config.json.

Alternatively, to open the configuration file via terminal:

On macOS:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows:
code %APPDATA%\Claude\claude_desktop_config.json
2. Add the Descope server configuration:
{
  "mcpServers": {
    "descope": {
      "command": "node",
      "args": ["/path/to/descope-mcp-server/build/index.js"],
      "env": {
        "DESCOPE_PROJECT_ID": "your-descope-project-id-here",
        "DESCOPE_MANAGEMENT_KEY": "your-descope-management-key-here"
      }
    }
  }
}

Replace your-descope-project-id-here and your-descope-management-key-here with your actual Descope Project ID and Management Key from app.descope.com/settings/project and app.descope.com/settings/company/managementkeys.

3. Restart Claude Desktop

To apply the changes:

  1. Fully quit Claude Desktop (ensure it's not just minimized).
  2. Relaunch Claude Desktop.
  3. Check for the 🔌 icon to confirm the Descope server is connected.

Claude Desktop with Descope MCP Server x5

Running the server

First, build the project:

npm run build
1. Running the server on stdio
npm run start:stdio
2. Running the server on SSE
npm run start:sse

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.