SharePoint

Provides a read-only MCP server to query live SharePoint data via the CData JDBC Driver.

other

0

GitHub Stars

other

Language

4 months ago

First Indexed

3 weeks 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-sharepoint-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/Salesforce.prp"
      ]
    }
  }
}

This MCP Server lets you query live SharePoint data through a simple, read-only interface powered by the CData JDBC Driver. It enables natural language questions to access SharePoint information without writing SQL, making it easy to retrieve up-to-date data for analytics, reporting, and AI-assisted insights.

How to use

You run the MCP Server locally and connect your AI client or natural language interface to it. The server exposes SharePoint data in a way that lets you ask questions like, “Show me all active accounts with recent activity” or “What are the open support tickets for the current quarter?” The built-in tools let you discover what data is available and then query it as needed. When you use a client that supports MCP servers, you simply point the client at your local server instance and start asking questions. There is no need to write SQL; your questions are translated into data-access operations behind the scenes.

How to install

Prerequisites: ensure you have Java installed on your machine. You will also need a Java development kit compatible with running MCP servers.

Build the MCP server package locally.

mvn clean install

# This creates the JAR file: CDataMCP-jar-with-dependencies.jar

Install the CData JDBC Driver for SharePoint and license it according to your platform.
Create a configuration file for the JDBC connection (example shown uses SharePoint as the data source). The file defines the JDBC URL and the tables you want to expose.

# Example sharepoint.prp (adjust paths and values to your environment)
Prefix=sharepoint
ServerName=CDataSharePoint
ServerVersion=1.0
DriverPath=/path/to/cdata.jdbc.sharepoint.jar
DriverClass=cdata.jdbc.sharepoint.SharePointDriver
JdbcUrl=jdbc:sharepoint:InitiateOAuth=GETANDREFRESH;
Tables=

Additional steps to configure and start

Next, create a Claude Desktop-like MCP configuration (or use your preferred MCP client) to point to the local server. You will reference the generated .prp file from the CLI that starts the MCP server.

Start the MCP Server using the runtime command.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/sharepoint.prp

Available tools

sharepoint_mcp_get_tables

Retrieves a list of tables available in the SharePoint data source. The result is returned in CSV format with column headers on the first line.

sharepoint_mcp_get_columns

Retrieves a list of columns for a specified table. The result is returned in CSV format with column headers on the first line.

sharepoint_mcp_run_query

Executes a SQL SELECT query against the SharePoint data source and returns the matching rows.