Sharepoint MCP Server by CData

@CDataSoftware

Basic information

About Sharepoint 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 SharePoint (beta)](https://www.cdata.com/download/download.aspx?sku=RSZK-V &type=beta).

#sharepoint #mcp-server #cdata

Sharepoint MCP Server by CData config

Add this server to your MCP-compatible client using the configuration below.

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

Sharepoint MCP Server by CData tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Sharepoint MCP Server by CData?

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

How to use Sharepoint MCP Server by CData?

Clone the repository, build the server with Maven (mvn clean install), download and license the CData JDBC Driver for SharePoint, use the connection string utility to configure a JDBC connection, and create a .prp properties file for your connection. Then add the server to your client's MCP configuration (e.g., claude_desktop_config.json). The server runs via stdio and must be on the same machine as the client.

Key features of Sharepoint MCP Server by CData

Read-only access to live SharePoint data
Powered by the CData JDBC Driver for SharePoint
Exposes SharePoint as relational SQL models
Three built-in MCP tools: get_tables, get_columns, run_query
Natural language querying via AI clients like Claude Desktop
Requires Java and Maven build environment

Use cases of Sharepoint MCP Server by CData

Ask natural language questions about your SharePoint data
Retrieve live SharePoint records for analysis via AI chat
Correlate SharePoint data without writing SQL manually
Integrate SharePoint data into Claude Desktop workflows
Explore available SharePoint tables and columns through AI conversation

Frequently asked questions

Is this server read-only?

Yes, this project builds a read-only MCP server. For full read, write, update, and delete capabilities, the README suggests the separate CData MCP Server for SharePoint (beta).

What dependencies are required to run the server?

Java and Maven are needed to build and run the server. You must also install and license the CData JDBC Driver for SharePoint.

How does the server connect to SharePoint?

The server connects via a JDBC connection string configured using the CData JDBC Driver's connection string builder utility. The connection details are stored in a `.prp` properties file.

What transport does the server use to communicate with clients?

The server communicates over stdio, so it can only be used with clients running on the same machine as the server.

What tools does the server expose to AI clients?

The server exposes three tools: `get_tables` (list available tables), `get_columns` (list columns for a specific table), and `run_query` (execute a SQL SELECT query).

Comments

More Other MCP servers

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.