@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 XML Documents (beta)](https://www.cdata.com/download/download.aspx?sku=DVZK-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\\xml-documents.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。
XML Documents MCP Server by CData is a read-only Model Context Protocol (MCP) server that allows large language models (LLMs) like Claude Desktop to query live XML Documents data using natural language. It wraps the CData JDBC Driver for XML Documents, which exposes XML data as relational SQL models, making the information accessible through a simple MCP interface without requiring SQL.
Clone the repository, build with Maven (mvn clean install), download and license the CData JDBC Driver for XML Documents, and create a .prp property file with your JDBC connection string. Add the server to your client’s MCP configuration (e.g., claude_desktop_config.json) by pointing to the built JAR and the property file. Once configured, you can ask natural language questions about the data; the server exposes tools like {servername}_get_tables, {servername}_get_columns, and {servername}_run_query (for SELECT queries).
This server is read-only; it only supports querying data. The full CData MCP Server for XML Documents (beta) provides read, write, update, delete, and action capabilities, along with a simplified setup.
You need Java (to run the JAR), Maven (to build), and the CData JDBC Driver for XML Documents installed and licensed on the same machine as the client.
Authentication is configured in the JDBC connection string. For OAuth-based data sources, the connection string utility will open a browser for authentication. The connection string is stored in the `.prp` file.
The server uses `stdio`, so it can only be used with clients running on the same machine as the server.
All data remains in the original XML source; the server does not persist or cache data locally.
Model Context Protocol Servers
MCP server for working with PDF files
MCP Server for reading many files at the same time
Go server implementing Model Context Protocol (MCP) for filesystem operations.
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
评论