MCP.so
ログイン
G

Google Search MCP Server by CData

@CDataSoftware

基本情報

カテゴリ

検索

トランスポート

stdio

作者

CDataSoftware

投稿者

Cameron Leblanc

Google Search 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 Google Search (beta): https://www.cdata.com/download/download.aspx?sku=BLZK-V&type=beta

Google Search 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\\google-search.prp"
      ]
    }
  }
}

Google Search 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 Google Search MCP Server by CData?

This is a read-only MCP server that uses the CData JDBC Driver for Google Search to let LLMs like Claude Desktop query live Google Search data via natural language questions — no SQL required.

How to use Google Search MCP Server by CData?

Clone the repository, build with mvn clean install, download and license the CData JDBC Driver for Google Search, then create a .prp file with your JDBC connection string. Add the server to your Claude Desktop config (claude_desktop_config.json) and run or refresh the client. The server runs over stdio and must be on the same machine as the client.

Key features of Google Search MCP Server by CData

  • Read-only access to Google Search data via MCP.
  • Uses CData JDBC Driver to expose Google Search as SQL models.
  • Built-in tools: get_tables, get_columns, run_query.
  • Works with natural language queries through AI clients.
  • Simple setup with a single JAR and property file.
  • Licensed under MIT License.

Use cases of Google Search MCP Server by CData

  • Ask an LLM to search Google for recent news about a topic.
  • Let Claude Desktop answer questions using live Google Search results.
  • Integrate Google Search into AI workflows without writing custom code.
  • Query Google Search alongside other data sources via the same MCP interface.

よくある質問

1

What does this MCP server do?

It allows LLMs to read Google Search data by issuing tools that run SQL-like queries through the CData JDBC Driver. The server is read-only; for full create, update, delete, and action capabilities, see the separate CData MCP Server for Google Search (beta).

2

How do I set up the server?

Clone the repo, run `mvn clean install`, download and license the CData JDBC Driver for Google Search, configure a `.prp` file with your JDBC connection string, then add the server to your MCP client’s config.

3

What tools are available?

Three tools: `{servername}_get_tables` (list tables), `{servername}_get_columns` (list columns for a table), and `{servername}_run_query` (execute a SQL SELECT query). You do not need to call them directly—just ask natural language questions.

4

Does the server require a database or special runtime?

It requires Java (to run the JAR) and the CData JDBC Driver for Google Search (trial or licensed). No database is needed; the driver connects directly to Google Search.

5

How does the server communicate with the client?

The server uses the `stdio` transport, so it must run on the same machine as the client. Authentication (e.g., OAuth) is handled by the JDBC driver during connection setup.

コメント

「検索」の他のコンテンツ