mcp-keycloak

mcp-keycloak

Managing Keycloak identity and access management

Category
访问服务器

README

Keycloak MCP Server

Integration Python Version MIT licensed smithery badge

A Model Context Protocol (MCP) server that provides a natural language interface for managing Keycloak identity and access management through its REST API. This server enables AI agents to perform user management, client configuration, realm administration, and role-based access control operations seamlessly.

Overview

The Keycloak MCP Server bridges the gap between AI applications and Keycloak's powerful identity management capabilities. Whether you're building an AI assistant that needs to manage users, configure clients, or handle complex authorization scenarios, this server provides the tools you need through simple, natural language commands.

Features

🔐 Comprehensive User Management

Manage users lifecycle from creation to deletion, including password resets, session management, and user attribute updates.

🏢 Client Configuration

Create and configure OAuth2/OIDC clients, manage client secrets, and handle service accounts programmatically.

👥 Role-Based Access Control

Define and assign realm and client-specific roles, manage user permissions, and implement fine-grained access control.

🏛️ Realm Administration

Configure realm settings, manage default groups, handle event configurations, and control realm-wide policies.

🔄 Group Management

Organize users into groups, manage group hierarchies, and handle group-based permissions efficiently.

Installation

Installing via Smithery

To install mcp-keycloak for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-keycloak --client claude

Quick Start

Install using pip:

pip install mcp-keycloak

Development Installation

Clone the repository and install dependencies:

git clone https://github.com/idoyudha/mcp-keycloak.git
cd mcp-keycloak
pip install -e .

Configuration

The server can be configured using environment variables or a .env file:

# Required configuration
SERVER_URL=https://your-keycloak-server.com
USERNAME=admin-username
PASSWORD=admin-password
REALM_NAME=your-realm

# Optional OAuth2 client configuration
CLIENT_ID=optional-client-id
CLIENT_SECRET=optional-client-secret

Tools

The Keycloak MCP Server provides a comprehensive set of tools organized by functionality:

User Management

Complete user lifecycle management including:

  • list_users - List users with pagination and filtering
  • create_user / update_user / delete_user - Full CRUD operations
  • reset_user_password - Password management
  • get_user_sessions / logout_user - Session control
  • count_users - User statistics

Client Management

OAuth2/OIDC client configuration:

  • list_clients / get_client / create_client - Client operations
  • get_client_secret / regenerate_client_secret - Secret management
  • get_client_service_account - Service account access
  • update_client / delete_client - Client modifications

Role Management

Fine-grained permission control:

  • list_realm_roles / create_realm_role - Realm role operations
  • list_client_roles / create_client_role - Client-specific roles
  • assign_realm_role_to_user / remove_realm_role_from_user - Role assignments
  • get_user_realm_roles / assign_client_role_to_user - User role queries

Group Management

Hierarchical user organization:

  • list_groups / create_group / update_group - Group operations
  • get_group_members / add_user_to_group - Membership management
  • get_user_groups / remove_user_from_group - User group associations

Realm Administration

System-wide configuration:

  • get_realm_info / update_realm_settings - Realm configuration
  • get_realm_events_config / update_realm_events_config - Event management
  • add_realm_default_group / remove_realm_default_group - Default settings

Usage

Running the Server

Start the MCP server directly:

python -m src.main

Integration Examples

Claude Desktop

  1. Clone the server:
git clone https://github.com/idoyudha/mcp-keycloak.git
  1. Configure in claude_desktop_config.json:
{
  "mcpServers": {
    "keycloak": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/mcp-keycloak",
        "run",
        "src/main.py"
      ],
      "env": {
        "SERVER_URL": "https://your-keycloak.com",
        "USERNAME": "admin",
        "PASSWORD": "admin-password",
        "REALM_NAME": "your-realm"
      }
    }
  }
}

Using uvx

{
  "mcpServers": {
    "keycloak": {
      "command": "uvx",
      "args": [
        "mcp-keycloak"
      ],
      "env": {
        "SERVER_URL": "https://your-keycloak.com",
        "USERNAME": "admin",
        "PASSWORD": "admin-password",
        "REALM_NAME": "your-realm"
      }
    }
  }
}

Example Use Cases

🤖 AI-Powered Identity Management

Build AI assistants that can handle user onboarding, permission management, and access control through natural language commands.

🔄 Automated User Provisioning

Create workflows that automatically provision users, assign roles, and configure client applications based on business rules.

📊 Identity Analytics

Query and analyze user data, session information, and access patterns to gain insights into your identity infrastructure.

🚀 DevOps Integration

Integrate Keycloak management into your CI/CD pipelines, allowing automated configuration of identity services.

Requirements

  • Python 3.8 or higher
  • Keycloak server (tested with Keycloak 18+)
  • Admin access to Keycloak realm

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

For issues, questions, or contributions, please visit the GitHub repository.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选