What are the prerequisites for running Okta MCP Server?
You need Node.js v16 or higher, the Claude Desktop App, an Okta Developer Account, and an Admin API Token from Okta.
@kapilduraphe
基本情報
Okta MCP Server
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A Model Context Protocol server that enables Claude to interact with Okta's user management system, providing comprehensive user and group management capabilities along with onboarding automation.
Install dependencies with npm install, then configure Claude Desktop by adding the server to claude_desktop_config.json with the command node, a path to dist/index.js, and environment variables OKTA_ORG_URL and OKTA_API_TOKEN. After restarting Claude Desktop, you can ask Claude to manage Okta users and groups using natural language.
You need Node.js v16 or higher, the Claude Desktop App, an Okta Developer Account, and an Admin API Token from Okta.
Install dependencies, build the project, then add the server to your Claude Desktop configuration with the command `node`, an absolute path to `dist/index.js`, and environment variables `OKTA_ORG_URL` (e.g., `https://dev-123456.okta.com`) and `OKTA_API_TOKEN`. Restart Claude Desktop to activate.
Supported operators include `eq` (exact match), `sw` (starts with), `ew` (ends with), `co` (contains), and `pr` (present). Not all attributes support all operators; the server automatically falls back to client-side filtering when needed.
The onboarding automation tools are experimental and may be subject to changes or limitations based on Okta’s API constraints. Use with caution in production environments.
The server uses the Okta API token and org URL provided as environment variables. API tokens should be kept secure, never committed to version control, and rotated regularly. PII masking is enabled for sensitive search parameters.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

The elmah.io MCP server allows AI assistants to interact directly with your error logs, deployments, and organization statistics. Debug production issues faster than ever before.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

コメント