Xml Documents

This read-only MCP Server allows you to connect to XML Documents data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for XML Documents (https://www.cdata.com/drivers/xml/download/mcp).

java

GitHub Stars

java

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-xml-documents-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/xml_documents.prp"
      ]
    }
  }
}

You can run a read-only MCP server that exposes live XML Documents data via the CData JDBC Driver. This server lets AI clients query the data in natural language without writing SQL, while keeping the data access secure and controlled through a simple MCP interface.

How to use

Once the MCP server is running, you connect your AI client to the local stdio-based MCP endpoint. Your client will discover the exposed MCP server and automatically use the built-in tools to inspect the data, read records, and answer complex questions about the XML Documents source. You can ask questions like which XML Documents contain specific values, or summarize data across multiple documents. No SQL knowledge is required; your client sends natural-language queries and the MCP layer translates them into data access actions.

How to install

Prerequisites you need before installing:

Java Runtime Environment (JRE) or JDK installed and available on your PATH
Maven or a Java build tool to compile the MCP server project
A CData JDBC Driver for XML Documents (license or trial) installed and configured on your system
Access to a live XML Documents data source via the CData JDBC Driver (for example, a Salesforce connection string setup) Follow these concrete steps to build and run the MCP server.

Install and run steps

# 1) Clone the project and move into the directory
git clone https://github.com/cdatasoftware/xml-documents-mcp-server-by-cdata.git
cd xml-documents-mcp-server-by-cdata

# 2) Build the server
mvn clean install

# 3) Ensure the CData JDBC Driver for XML Documents is installed and licensed
# - Download from the CData site and install per your OS
# - License the driver (adjust paths to your installation)
java -jar cdata.jdbc.xml.jar --license

# 4) Configure your JDBC connection and create a .prp file (xml_documents.prp)
# - Use the Connection String utility to build a JDBC URL and test the connection
# - Copy the resulting JDBC URL for the prp file

# 5) Start the MCP server (stdio) using the example prp file
java -jar CDataMCP-jar-with-dependencies.jar /PATH/TO/xml_documents.prp

Configure the MCP client integration

Create an MCP config entry in your client (Claude Desktop, if you use it, or your own client) that points to the local MCP server. Use the stdio startup pattern shown below, replacing paths with your actual file locations.

{
  "mcpServers": {
    "xml_documents": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/xml_documents.prp"
      ]
    }
  }
}

Available tools

xml_documents_get_tables

Retrieves a list of tables (XML Document collections exposed as relational-like tables). The tool returns CSV with column headers as the first line.

xml_documents_get_columns

Retrieves a list of columns for a given table. The tool returns CSV with column headers as the first line.

xml_documents_run_query

Executes a SQL SELECT query against the exposed XML Document data.

Built by

VeilStrat

AI signals for GTM teams