restic-mcp

restic-mcp

An MCP server that enables AI assistants to manage restic backups, including listing snapshots, browsing files, and creating new backups. It provides tools for repository maintenance, data restoration, and applying retention policies through the Model Context Protocol.

Category
访问服务器

README

restic-mcp

An MCP server for managing restic backups. Lets AI assistants list snapshots, browse backed-up files, create backups, apply retention policies, and more — all through the Model Context Protocol.

Tools

Read-only

Tool Description
list_snapshots List snapshots, with optional filters by host, tags, or paths
browse_snapshot List files and directories inside a snapshot
diff_snapshots Show what changed between two snapshots
find_files Search for files by name or glob pattern across snapshots
repo_stats Repository size, file count, and deduplication statistics
check_repo Verify repository integrity

Write

Tool Description
create_backup Back up files/directories with optional tags and exclusions
forget_snapshots Remove snapshots by ID or retention policy (keep-last, keep-daily, etc.)
prune_repo Remove unreferenced data to reclaim disk space
restore_snapshot Restore files from a snapshot to a target directory
tag_snapshot Add or remove tags on a snapshot
unlock_repo Remove stale repository locks

Requirements

  • Python 3.10+
  • restic installed and in PATH
  • uv (recommended) or pip

Installation

git clone https://github.com/mohsenil85/restic-mcp.git
cd restic-mcp
uv sync

Configuration

The server reads repository credentials from environment variables:

Variable Description
RESTIC_REPOSITORY Path or URL to the restic repository
RESTIC_PASSWORD Repository password
RESTIC_PASSWORD_COMMAND Command that prints the password (alternative to RESTIC_PASSWORD)

Every tool also accepts an optional repo parameter to override RESTIC_REPOSITORY per-call.

Usage

Claude Code

Add to ~/.claude.json:

{
  "mcpServers": {
    "restic": {
      "command": "uv",
      "args": ["--directory", "/path/to/restic-mcp", "run", "restic-mcp"],
      "env": {
        "RESTIC_REPOSITORY": "/path/to/your/repo",
        "RESTIC_PASSWORD_COMMAND": "pass show restic"
      }
    }
  }
}

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "restic": {
      "command": "uv",
      "args": ["--directory", "/path/to/restic-mcp", "run", "restic-mcp"],
      "env": {
        "RESTIC_REPOSITORY": "/path/to/your/repo",
        "RESTIC_PASSWORD": "your-password"
      }
    }
  }
}

MCP Inspector

Test the server interactively:

RESTIC_REPOSITORY=/path/to/repo RESTIC_PASSWORD=test uv run mcp dev src/restic_mcp/server.py

Architecture

MCP Client (Claude, Cursor, etc.)
    │
    │  stdio (JSON-RPC)
    ▼
restic-mcp server (FastMCP)
    │
    │  subprocess (async)
    ▼
restic CLI  ──►  repository (local, S3, B2, SFTP, ...)

The server is a thin async wrapper around the restic CLI. It calls restic with --json where supported for structured output, falling back to text parsing otherwise. No direct repository access — all operations go through the official restic binary.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选