Microsoft OneDrive MCP Server by CData
@CDataSoftware
Microsoft OneDrive MCP Server by CData について
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 Microsoft OneDrive (beta)](https://www.cdata.com/download/download.aspx?sku=UOZK-V&type=beta).
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"{classname_dash}": {
"command": "PATH\\TO\\java.exe",
"args": [
"-jar",
"PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
"PATH\\TO\\microsoft-onedrive.prp"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Microsoft OneDrive MCP Server by CData?
Microsoft OneDrive MCP Server by CData is a read-only MCP server that lets LLMs query live Microsoft OneDrive data through the CData JDBC Driver for Microsoft OneDrive. The driver exposes OneDrive data as relational SQL models, and the server wraps it into a simple MCP interface so you can ask natural language questions without writing SQL.
How to use Microsoft OneDrive MCP Server by CData?
Clone the repository, build with mvn clean install, then install and license the CData JDBC Driver for Microsoft OneDrive. Create a .prp file with connection details (Prefix, ServerName, DriverPath, DriverClass, JdbcUrl). Configure Claude Desktop (or another MCP client) by adding the server to claude_desktop_config.json with the path to java and the compiled JAR and .prp file. The server runs over stdio and must be on the same machine as the client.
Key features of Microsoft OneDrive MCP Server by CData
- Read-only access to Microsoft OneDrive data via MCP tools
- Uses CData JDBC Driver for Microsoft OneDrive
- Natural language queries – no SQL required
- Supports listing tables, columns, and running SELECT queries
- OAuth-based authentication for Microsoft OneDrive
Use cases of Microsoft OneDrive MCP Server by CData
- Query live OneDrive files and metadata using conversational AI
- Enable LLMs to answer questions about OneDrive content
- Integrate OneDrive data into AI workflows without a separate sync
FAQ from Microsoft OneDrive MCP Server by CData
Is this server read-only?
Yes. The README explicitly states that this project builds a read-only MCP server. For full read/write/update/delete capabilities, CData offers a separate free beta MCP Server.
How do I authenticate to Microsoft OneDrive?
Authentication uses OAuth via the CData JDBC Driver. When you configure the connection string (e.g., jdbc:onedrive:InitiateOAuth=GETANDREFRESH;), the driver will launch a browser for you to log in and grant access.
What transport does the server use?
The server uses stdio as its transport, meaning it runs as a local process and communicates over standard input/output. It can only be used with MCP clients that run on the same machine.
Do I need a license for the CData JDBC Driver?
Yes. You must download and install the CData JDBC Driver for Microsoft OneDrive and license it (either with a trial key or a purchased license) before the server can connect.
What tools are available?
The server exposes three main tools: {servername}_get_tables (list all tables), {servername}_get_columns (list columns for a given table), and {servername}_run_query (execute a SQL SELECT query). Output is returned in CSV format.
「ファイルとストレージ」の他のコンテンツ
S3 MCP Server
samuraikunMCP server to integrate AWS S3 and LLM
Filesystem MCP Server for WSL
webconsultingfilesystem MCP server for accessing WSL distributions from Windows
mcp-rquest
xxxbrianA 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.
PDF Tools MCP
danielkennedy1File Context Server
bsmi021A Model Context Protocol (MCP) server that provides file system context to Large Language Models (LLMs). This server enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.
コメント