MCP.so
ログイン

Cloudera AI Agent Studio MCP Server

@jasonmeverett

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

jasonmeverett

Cloudera AI Agent Studio MCP Server について

MCP Server for driving Cloudera AI's Agent Studio

Cloudera AI Agent Studio MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agent-studio": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/cloudera-ai-agent-studio-mcp",
        "run",
        "serve.py"
      ],
      "env": {
        "CDSW_APIV2_KEY": "YOUR-TOKEN-HERE",
        "AGENT_STUDIO_DOMAIN": "https://your-studio.CDSW_DOMAIN.cldr.work"
      }
    }
  }
}

Cloudera AI Agent Studio MCP Server のツール

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。

概要

What is Cloudera AI Agent Studio MCP Server?

Cloudera AI Agent Studio MCP Server is a lightweight Model Context Protocol (MCP) bridge that exposes an Agent Studio instance as callable tools. It lets Claude or any MCP-aware client list, inspect, and build Agent Studio workflows on the fly.

How to use Cloudera AI Agent Studio MCP Server?

Integrate with Claude Desktop by adding an entry to claude_desktop_config.json specifying the uv command, the path to the server directory, and required environment variables (CDSW_APIV2_KEY and AGENT_STUDIO_DOMAIN). Once connected, tools such as list_current_workflows(), get_workflow_information(), create_workflow(), and others become available.

Key features of Cloudera AI Agent Studio MCP Server

  • List all workflows with IDs and names
  • Fetch full JSON metadata for one workflow
  • Create a new blank workflow
  • Add a conversational task to a workflow
  • Add a manager agent as supervisor
  • Add additional agents to expand the crew

Use cases of Cloudera AI Agent Studio MCP Server

  • Populate a UI drop-down of existing workflow projects
  • Inspect tasks, agents, and process settings of a workflow
  • Automate project scaffolding with new blank workflows
  • Turn a static workflow into a chat-first experience
  • Build hierarchical or delegated workflows with a manager agent

よくある質問

1

What is the Cloudera AI Agent Studio MCP Server?

It is a lightweight MCP bridge that exposes Agent Studio workflows as callable tools for MCP-aware clients like Claude.

2

How do I integrate it with Claude Desktop?

Add an entry to your `claude_desktop_config.json` with the `uv` command, server directory path, and the environment variables `CDSW_APIV2_KEY` and `AGENT_STUDIO_DOMAIN`.

3

What tools does the server expose?

The server provides six tools: `list_current_workflows`, `get_workflow_information`, `create_workflow`, `make_workflow_conversational`, `add_manager_agent_to_workflow`, and `add_agent_to_workflow`.

4

What environment variables are required?

You need `CDSW_APIV2_KEY` for authentication and `AGENT_STUDIO_DOMAIN` for the studio URL.

5

Can I use it with MCP clients other than Claude?

Yes, the server works with any MCP-aware client, not just Claude.

コメント

「AI とエージェント」の他のコンテンツ