GraphQL MCP Server by CData

Name: GraphQL MCP Server by CData
Author: CDataSoftware

@CDataSoftware

关于 GraphQL MCP Server by CData

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 GraphQL (beta)](https://www.cdata.com/download/download.aspx?sku=LAZK-V&type=beta).

#graphql #mcp-server #cdata

基本信息

分类

其他

传输方式

stdio

发布者

CDataSoftware

提交者

Cameron Leblanc

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "{classname_dash}": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\graphql.prp"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is GraphQL MCP Server by CData?

GraphQL MCP Server by CData is a read-only Model Context Protocol server that allows LLMs (like Claude Desktop) to query live GraphQL data using natural language. It wraps the CData JDBC Driver for GraphQL, which exposes GraphQL endpoints as relational SQL models, so no SQL is required from the user.

How to use GraphQL MCP Server by CData?

Clone the repository, build with Maven (mvn clean install), download and license the CData JDBC Driver for GraphQL, configure a connection string using the driver’s utility, create a .prp property file with the JDBC connection details, then add the server to Claude Desktop’s mcpServers config. The server communicates over stdio and must run on the same machine as the client.

Key features of GraphQL MCP Server by CData

Read-only access to live GraphQL data via natural language queries
Wraps the CData JDBC Driver for GraphQL as a relational SQL model
Provides get_tables, get_columns, and run_query tools
Supports OAuth-based authentication for data sources
Simple setup with a single JAR file and a properties file

Use cases of GraphQL MCP Server by CData

Ask an LLM to summarize data trends from a GraphQL endpoint
Let users query live GraphQL data without writing SQL
Automate data retrieval from GraphQL APIs for AI-driven analysis
Enable data exploration of GraphQL-backed systems using conversational interfaces

FAQ from GraphQL MCP Server by CData

What are the dependencies and runtime requirements?

Java Runtime Environment (JRE) and Maven (for building) are required. The CData JDBC Driver for GraphQL must be downloaded and licensed separately. The server runs as a standalone JAR file.

What transport does the server use? How does authentication work?

The server uses stdio transport, so it must be run on the same machine as the MCP client. Authentication (e.g., OAuth) is handled during JDBC connection string configuration using the driver’s connection utility.

Is this server read-only? Can it write data?

Yes, this project explicitly builds a read-only MCP server. For full read, write, update, delete, and action capabilities, CData offers a separate free beta MCP server for GraphQL.

Where does the data live? Is it cached?

Data is fetched live from the configured GraphQL endpoint. No caching is performed by the server; each query retrieves fresh data from the data source.

What are known limitations?

The server is read-only and operates only via stdio. It cannot be used with remote MCP clients. The connection string must be configured manually via the JDBC driver utility.