MCP.so
登录

Google Drive MCP Server

@festusev

代码仓库

关于 Google Drive MCP Server

An MCP Server for Google Drive

#google-drive#mcp#server

基本信息

分类

文件与存储

运行时

python

传输方式

stdio

发布者

festusev

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "google_drive_mcp": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

工具

未检测到工具

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。

概览

What is Google Drive MCP Server?

Google Drive MCP Server is a Model Context Protocol (MCP) server built with FastMCP that provides tools for reading, writing, searching, and listing files in Google Drive, with a focus on Google Docs operations. It is designed for developers and AI agents who need to programmatically interact with Google Drive using service account authentication.

How to use Google Drive MCP Server?

After installing dependencies with uv sync, enable the Google Drive and Google Docs APIs, create a service account, and save its key file as service-account-key.json in the project root. Share target Drive files/folders with the service account email. Run python -m google_drive_mcp.server – no interactive authentication flow is required.

Key features of Google Drive MCP Server

  • List files with optional folder, MIME type, and pagination.
  • Search files using Google Drive query syntax.
  • Read Google Docs content with pagination and tab selection.
  • Write or replace content in Google Docs with tab and range controls.
  • Service account authentication for server‑to‑server access.

Use cases of Google Drive MCP Server

  • Search for Google Docs containing specific keywords.
  • Read large documents in paginated chunks.
  • Write data to a specific tab or insertion point in a document.
  • List and filter files in a shared folder.
  • Replace existing content in a document using start/end indices.

FAQ from Google Drive MCP Server

What tools does Google Drive MCP Server provide?

It provides four tools: list_files, search_files, read_document, and write_document.

How do I authenticate?

Authentication uses a service account key file placed as service-account-key.json in the project root. No OAuth user flow is needed.

What are the runtime dependencies?

Python, uv for dependency management, and the FastMCP library with Google API client libraries (installed via uv sync).

How does pagination work for files and documents?

File listing accepts page_token and page_size (max 100). Document reading accepts start_index and length (max 10,000 characters) to navigate parts of a document.

Can I access files not shared with the service account?

No. Any file or folder you want to access must be explicitly shared with the service account’s email address.

评论

文件与存储 分类下的更多 MCP 服务器

box-mcp-server

hmk

A Box model context protocol server to search, read and access files

11

PDF Extraction MCP Server (Claude Code Fork)

xraywu

MCP server to extract contents from a PDF file

31

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

shtse8

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810

File Context Server

bsmi021

A 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.

37

Filesystem MCP Server for WSL

webconsulting

filesystem MCP server for accessing WSL distributions from Windows

14