Rclone MCP
R

Rclone MCP

rclone-mcp is an MCP server based on the Rclone remote control API. It allows AI assistants to manage cloud storage, synchronize files, list directories, etc. through natural language, and supports multiple toolsets and read-only mode.
2 points
3.4K

What is rclone-mcp?

rclone-mcp is a server based on the Model Context Protocol (MCP). It connects AI assistants with the Rclone Remote Control (RC) API. Through this server, AI assistants (such as Claude, Cursor, etc.) can manage cloud storage services just like human users, including more than 40 storage services such as Google Drive, Dropbox, OneDrive, Amazon S3, etc.

How to use rclone-mcp?

Using rclone-mcp requires three steps: 1) Run the Rclone remote control daemon; 2) Add the rclone-mcp server to the AI assistant configuration; 3) Issue storage management instructions to the AI assistant through natural language. There is no need to write complex commands throughout the process, and the AI assistant will understand your intentions and perform corresponding operations.

Use cases

rclone-mcp is particularly suitable for users who need to manage cloud files frequently, such as: developers need to back up code to the cloud, teams need to synchronize project files, individual users manage multiple cloud storage accounts, content creators organize media files, etc. Through the AI assistant, these operations become as simple as having a conversation.

Main features

Automatically generated toolset
Automatically generate 98 API endpoint tools based on the rclone-openapi specification, no manual configuration required
Modular toolset
14 optional toolset groups, specific functions can be enabled as needed to keep the tool list concise
Read-only mode
A security mode that only allows viewing operations to prevent the AI assistant from accidentally modifying or deleting files
Multiple transport protocols
Supports both stdio and HTTP transport methods to meet the needs of different clients
Docker containerization
Provides a Docker image for easy deployment and use in various environments
Authentication support
Supports HTTP Basic authentication to ensure a secure connection with the Rclone RC API
Advantages
Natural language operation: No need to memorize complex commands, manage cloud storage with daily language
Highly integrated: Seamlessly integrated with mainstream AI assistants, such as Claude Desktop, Cursor, etc.
Flexible configuration: Toolsets can be enabled as needed to avoid excessive functionality
Security guarantee: Provides read-only mode to prevent misoperations
Cross-platform support: Supports Windows, macOS, Linux, and Docker environments
Limitations
Dependent on Rclone: Rclone remote control service needs to be installed and configured first
Network requirements: A stable network connection is required to access the Rclone RC API
Learning curve: Some technical knowledge is required for initial configuration
Function limitations: Limited by the capabilities of the Rclone API, some advanced functions may not be available

How to use

Start the Rclone remote control service
First, you need to run the Rclone remote control daemon on the local machine or server. This is the basis for rclone-mcp to communicate with cloud storage.
Configure the AI assistant
According to the AI assistant you are using (Claude Desktop or Cursor), add the rclone-mcp server settings to the configuration file.
Select the toolset
Select the appropriate toolset according to your needs. By default, it includes four toolsets: core, configuration, operation, and synchronization, with a total of 55 tools.
Start using
Restart the AI assistant. Now you can manage cloud storage through natural language instructions.

Usage examples

Cloud file browsing
When you need to quickly view the file structure in cloud storage, you can directly ask the AI assistant without logging in to the web interface.
Automatic backup and synchronization
Regularly synchronize important local folders to the cloud to ensure data security.
Cross-cloud storage migration
Migrate files from one cloud storage service to another.
Batch file management
Perform unified operations on a large number of files, such as renaming, moving, or deleting.

Frequently Asked Questions

Which cloud storage services does rclone-mcp support?
Is it safe to use rclone-mcp?
Do I need programming knowledge to use it?
Will rclone-mcp affect the performance of my AI assistant?
How to update rclone-mcp?
Can it be shared and used in a team?

Related resources

Rclone official website
Rclone project homepage, including complete documentation and downloads
Model Context Protocol specification
Official specification document of the MCP protocol
rclone-openapi project
Source of the OpenAPI specification used by rclone-mcp
rclone-sdk client
JavaScript SDK on which rclone-mcp is based
Rclone Discord community
Get help and communicate with other users
Claude Desktop configuration guide
How to configure Claude Desktop to use the MCP server

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "rclone": {
      "command": "npx",
      "args": ["-y", "rclone-mcp"],
      "env": {
        "RCLONE_URL": "http://localhost:5572"
      }
    }
  }
}

{
  "mcpServers": {
    "rclone": {
      "command": "npx",
      "args": ["-y", "rclone-mcp"],
      "env": {
        "RCLONE_URL": "http://localhost:5572",
        "RCLONE_USER": "admin",
        "RCLONE_PASS": "secret"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.6K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.7K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
5.8K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
5.7K
4 points
P
Paperbanana
Python
7.1K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
7.2K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.9K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.9K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.3K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.9K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.7K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
36.4K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
33.5K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.1K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.5K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
99.4K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase