mcpField
O
Onedrive

Onedrive

Remote
pipeworx.ioFiles & Storage0Updated 5w ago

About Onedrive

Onedrive is an MCP server for browsing and retrieving files in a user's OneDrive through Microsoft Graph. It helps connected-account users find documents, inspect file details, read supported text content, and review shared items and drive usage.

Key features

  1. 01List files and folders
  2. 02Search names and file contents
  3. 03Retrieve file and folder metadata
  4. 04Read text, Markdown and CSV content
  5. 05List shared items and drive profile

Use cases

  1. 01Finding a document by keyword
  2. 02Reading a text or CSV file
  3. 03Checking shared files and storage usage

MCP support

Exposes OneDrive file browsing, search, metadata, content, shared-item, and profile tools to MCP clients. It can run locally over stdio or connect through Pipeworx; gateway use requires a connected Microsoft account.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/onedrive/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-onedrive

OneDrive (Microsoft Graph) MCP Pack

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
onedrive_list_filesList files and folders in a OneDrive (Microsoft 365) folder. Pass a folder path relative to the drive root (e.g. "Documents" or "Documents/Reports"); omit to list the root. Returns each item's id, name, size, whether it is a folder, last-modified time, and web URL. Use to browse a user's OneDrive documents.
onedrive_search_filesSearch a user's OneDrive (Microsoft 365) for files and folders matching a query string across file names and content. Returns matching items with id, name, size, folder flag, last-modified time, and web URL. Use to find documents by keyword.
onedrive_get_fileGet full metadata for a single OneDrive (Microsoft 365) file or folder by its item id. Returns id, name, size, folder/file info, created and last-modified times, web URL, and parent reference. Use after listing or searching to inspect one document.
onedrive_get_file_contentDownload and return the text content of a OneDrive (Microsoft 365) file by its item id. Best for plain-text, Markdown, and CSV files; binary formats (Office docs, PDFs, images) will return unreadable bytes. Content is capped at ~100,000 characters and flagged when truncated.
onedrive_list_sharedList files and folders that have been shared with the user in OneDrive / Microsoft 365 ("Shared with me"). Returns each item's name, web URL, and who shared it. Use to find documents shared by colleagues.
onedrive_get_profileGet the user's OneDrive (Microsoft 365) drive profile: drive type, storage quota used and total (in bytes), and the owner display name. Use to report storage usage or confirm the connected account.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "onedrive": {
      "url": "https://gateway.pipeworx.io/onedrive/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/onedrive/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

This pack runs against a connected microsoft account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect microsoft, then call POST https://gateway.pipeworx.io/v1/tools/onedrive_list_files with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/onedrive_list_files. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "onedrive": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-onedrive"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-onedrive

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Onedrive data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.