MCP.so
ログイン
M

MarkLogic MCP Server by CData

@CDataSoftware

基本情報

カテゴリ

その他

トランスポート

stdio

作者

CDataSoftware

投稿者

Cameron Leblanc

MarkLogic MCP Server by CData について

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for MarkLogic (beta): https://www.cdata.com/download/download.aspx?sku=OMZK-V&type=beta

MarkLogic MCP Server by CData 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": {
    "{classname_dash}": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\marklogic.prp"
      ]
    }
  }
}

MarkLogic MCP Server by CData 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 MarkLogic MCP Server by CData?

MarkLogic MCP Server by CData is a read-only Model Context Protocol (MCP) server that allows LLMs (such as Claude Desktop) to query live data from MarkLogic using natural language, without requiring SQL. It wraps the CData JDBC Driver for MarkLogic, which exposes MarkLogic data as relational SQL models.

How to use MarkLogic MCP Server by CData?

Clone the repository, build with Maven (mvn clean install), install and license the CData JDBC Driver for MarkLogic, configure a .prp file with the JDBC connection string, then add the server to the Claude Desktop config file (claude_desktop_config.json). Restart Claude Desktop to query your MarkLogic data.

Key features of MarkLogic MCP Server by CData

  • Reads MarkLogic data via natural language queries
  • Exposes three built-in tools: get_tables, get_columns, run_query
  • Uses the CData JDBC Driver for MarkLogic as its data connector
  • Communicates via stdio transport (local client only)
  • Licensed under the MIT License
  • Supports MarkLogic and many other data sources with separate servers

Use cases of MarkLogic MCP Server by CData

  • Ask an LLM to summarize trends in your MarkLogic data
  • Retrieve specific records without writing SQL
  • Let an AI assistant explore available tables and columns
  • Correlate business metrics across MarkLogic datasets

よくある質問

1

Is this server read-only?

Yes. The README explicitly states this project builds a read-only MCP server. For full read, write, update, delete, and action capabilities, CData offers a separate beta MCP Server for MarkLogic.

2

What are the runtime dependencies?

You need Java (to run the JAR), Maven (to build), and the CData JDBC Driver for MarkLogic installed and licensed on the same machine.

3

Where does the data live?

The data stays in your MarkLogic instance. The server queries it live over JDBC and does not store data locally.

4

What transport does the server use?

The server uses `stdio` transport, so it can only run with clients on the same machine as the server.

5

How is authentication handled?

Authentication is configured in the JDBC connection string. For OAuth-based connections, you must authenticate in your browser when testing the connection via the CData JDBC Driver utility.

コメント

「その他」の他のコンテンツ