広告掲載
MCP.so
ログイン
C

CockroachDB MCP Server by CData

@CDataSoftware

リポジトリ

基本情報

カテゴリ

データベース

トランスポート

stdio

作者

CDataSoftware

投稿者

Cameron Leblanc

CockroachDB 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 CockroachDB (beta): https://www.cdata.com/download/download.aspx?sku=HJZK-V&type=beta

#cockroachdb#mcp-server#cdata

CockroachDB 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\\cockroachdb.prp"
      ]
    }
  }
}

CockroachDB 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 CockroachDB MCP Server by CData?

CData’s read-only MCP Server for CockroachDB wraps the CData JDBC Driver for CockroachDB, allowing LLMs like Claude Desktop to query live CockroachDB data via natural language. It exposes CockroachDB tables as SQL models through the Model Context Protocol.

How to use CockroachDB MCP Server by CData?

Clone the repository, build with Maven (mvn clean install), download and install the CData JDBC Driver, license it, configure a .prp file with connection details, then add the server to your client’s MCP configuration (e.g., claude_desktop_config.json). The server runs via java -jar CDataMCP-jar-with-dependencies.jar <path_to>.prp and communicates over stdio.

Key features of CockroachDB MCP Server by CData

  • Read-only access to CockroachDB data via MCP
  • Three built-in tools: get_tables, get_columns, run_query
  • Natural language queries – no SQL required by the user
  • Powered by the CData JDBC Driver for CockroachDB
  • Standard MCP interface compatible with Claude Desktop
  • MIT licensed and open source

Use cases of CockroachDB MCP Server by CData

  • AI assistants answering business questions from live CockroachDB tables
  • Customer support triage by querying ticket databases without SQL
  • Sales analytics dashboards powered by natural language requests
  • Automated reporting of real-time CockroachDB data in chat interfaces

よくある質問

1

Is this server read-only?

Yes. The README explicitly states it is a read-only MCP server. For full CRUD capabilities, CData offers a separate free beta server.

2

What are the runtime requirements?

Java (to run the built JAR), Maven (to build), and the CData JDBC Driver for CockroachDB (downloaded and licensed separately) are required.

3

How is the server started?

Execute `java -jar CDataMCP-jar-with-dependencies.jar /PATH/TO/cockroachdb.prp` from the command line after building the JAR and configuring the `.prp` file.

4

What transport protocol does the server use?

The server uses `stdio` transport, so it can only be used with clients running on the same machine.

5

Are there example JSON-RPC requests?

Yes. The README provides JSON-RPC 2.0 examples for `cockroachdb_get_tables`, `cockroachdb_get_columns`, and `cockroachdb_run_query`.

コメント

「データベース」の他のコンテンツ

Schemity

tbson

Local database MCP server: your agent sees a migration's impact before it runs, for PostgreSQL, MySQL, SQL Server and SQLite, with no database credentials.

Multi Database MCP Server

FreePeak

A powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.

397

mcp-server-qdrant: A Qdrant MCP server

qdrant

An official Qdrant Model Context Protocol (MCP) server implementation

637

MCP Alchemy

runekaagaard

A MCP (model context protocol) server that gives the LLM access to and knowledge about relational databases like SQLite, Postgresql, MySQL & MariaDB, Oracle, and MS-SQL.

412

Sail MCP Server for Spark SQL

lakehq

Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.

3.1K
広告掲載