What does this server do differently from the CData MCP Server for API Driver (beta)?
This server is read-only; the beta server supports full CRUD operations and offers a simplified setup.
@CDataSoftware
基本信息
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 API Driver (beta): https://www.cdata.com/download/download.aspx?sku=FAZK-V&type=beta
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\\api-driver.prp"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
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。
API Driver MCP Server by CData is a read-only Model Context Protocol (MCP) server that lets AI assistants like Claude Desktop query live data from any API source supported by the CData JDBC Driver for API Driver. It wraps the driver’s relational SQL model into a simple MCP interface, so users can ask natural language questions — no SQL required.
Clone the repository, build with mvn clean install, download and license the CData JDBC Driver for API Driver, then create a .prp file with connection properties (Prefix, ServerName, DriverPath, DriverClass, JdbcUrl, etc.). Configure your MCP client (e.g., Claude Desktop) to run java -jar CDataMCP-jar-with-dependencies.jar /path/to/file.prp using the stdio transport.
This server is read-only; the beta server supports full CRUD operations and offers a simplified setup.
Java and Maven are required. You must also download, install, and license the CData JDBC Driver for API Driver.

Layro connects your AI coding tool (Cursor, Claude Code, VS Code, Windsurf, Codex, Gemini CLI) to 112 production React, TypeScript and Tailwind CSS components. Your agent can search the library, read each component's pro

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a
评论