Skip to main content
Glama
duplicacy-mcp

duplicacy-mcp

duplicacy-mcp

MCP server for administering Duplicacy backups through the duplicacy-web API (the same internal HTTP API the web UI uses). Lets AI clients inspect storages, repositories, schedules and jobs, and create or delete them.

Built with the official Python MCP SDK 2.x (MCPServer, stdio transport).

Tools

Tool

Purpose

get_schedule_status

Schedules, next runs, running jobs

get_backup_status

Per-repository last-run status

lookup_storage

Storage existence + details

create_storage

New destination (local path or b2://, s3://, …) with encryption password

delete_storage

Remove a storage config (backups kept)

list_repositories

Repository IDs in a storage

create_repository

New source → storage pair

delete_repository

Remove a repository config (backups kept)

get_filters / set_filters

Repository include/exclude patterns

create_schedule / delete_schedule

Daily/weekly schedule containers

add_job / delete_job

backup / prune / check jobs within a schedule

start_stop_schedule

Enable / disable a schedule

Related MCP server: duplicacy-mcp

Setup

uv sync
uv run duplicacy-mcp

Configuration via environment:

Variable

Default

Purpose

DUPLICACY_WEB_URL

http://localhost:3875

duplicacy-web base URL

DUPLICACY_COMPUTER

localhost

Computer name in duplicacy-web

Client configuration

{
  "mcpServers": {
    "duplicacy": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/duplicacy-mcp", "run", "duplicacy-mcp"]
    }
  }
}

Notes

  • The duplicacy-web API is unauthenticated unless an administration token is set in the web UI. Keep the server on a trusted network.

  • Storage passwords are the repository encryption keys — callers must supply them when creating a storage and store them somewhere safe (e.g. Infisical).

Available Tools

15 tools
add_jobA

Add a job (backup, prune, or check) to a schedule.

Args: schedule_index: Schedule index (0-based). type: Job type: "backup", "prune", or "check". repository: Repository index (0-based). destination: Storage name the job writes to (or reads from for prune/check). source: Source path for backup jobs (e.g. /source/plex); empty for prune/check. options: Extra duplicacy CLI options. Backup example: "-threads 4". Prune example: "-keep 0:30 -a" (keep the 30 newest snapshots). Check example: "-fossils". parallel: Whether the job may run in parallel with others.

Inputs: type (required), repository (required), destination (required), schedule_index (required), +3 more. Returns: result

create_repositoryA

Create a backup repository: one source directory backed up to one storage.

Args: id: Repository ID, unique per computer (e.g. Plex-media). path: Source directory inside the duplicacy-web container (e.g. /source/plex). storage: Destination storage name.

Inputs: id (required), path (required), storage (required). Returns: result

create_scheduleA

Create a backup schedule (container for one or more jobs).

Args: name: Schedule name, unique in duplicacy-web. start_time: Daily start time as HH:MMAM/PM, e.g. "02:00AM" or "10:35AM". frequency: Interval in seconds (86400 = daily). days: 7-char bitmask of active weekdays, built Sunday-first, "1111111" = every day, "0000000" = never (disabled). max_time: Latest time of day the schedule may start, HH:MMAM/PM. "00:00" = no limit.

Inputs: name (required), start_time (required), days, max_time, +1 more. Returns: result

create_storageA

Create a new backup storage (destination).

Args: name: Storage name, unique in duplicacy-web. url: Storage URL. Local path (e.g. /backups/plex), or scheme URLs like b2://bucket, s3://..., sftp://user@host/path. password: Encryption password for the repository. Keep it safe; all backups in this storage are encrypted with it. compression: Chunk compression. One of lz4, zstd_default, zstd_fastest, zstd_better, zstd_best. lz4 suits already-compressed media. copy_from: Name of an existing storage to copy chunk files from (dedupe seeding). Empty string for a fresh storage.

Inputs: url (required), name (required), password (required), copy_from, +1 more. Returns: result

delete_jobB

Remove a job from a schedule.

Args: schedule_index: Schedule index (0-based). job_index: Job index within the schedule (0-based).

Inputs: job_index (required), schedule_index (required). Returns: result

delete_repositoryA

Delete a repository configuration. Existing backups remain in storage.

Args: index: Repository index (0-based, as shown by get_backup_status).

Inputs: index (required). Returns: result

delete_scheduleA

Delete a schedule and its jobs.

Args: schedule_index: Schedule index (0-based, as shown by get_schedule_status).

Inputs: schedule_index (required). Returns: result

delete_storageA

Delete a storage configuration. Existing backups in it are NOT deleted.

Args: name: Storage name to remove.

Inputs: name (required). Returns: result

get_backup_statusA

Return per-repository backup status (last run outcome, timestamps, sizes).

Inputs: no named parameters. Returns: result

get_filtersA

Return the include/exclude filter patterns of a repository.

Args: index: Repository index (0-based).

Inputs: index (required). Returns: result

get_schedule_statusA

Return schedule status: each schedule's next run, pause state, and running jobs.

Use this to see whether a backup is running or when the next one is due.

Inputs: no named parameters. Returns: result

list_repositoriesB

List backup repository IDs that exist in a storage.

Args: storage: Storage name.

Inputs: storage (required). Returns: result

lookup_storageA

Look up a storage by name; returns whether it exists and its details.

Args: name: Storage name as configured in duplicacy-web.

Inputs: name (required). Returns: result

set_filtersA

Set the include/exclude filter patterns of a repository.

Patterns are duplicacy filter rules, one per entry, first match wins: +dir/* includes, -* excludes everything else. E.g. ["+movies/", "+tv/", "-*"] backs up only movies and tv.

Args: index: Repository index (0-based). patterns: Filter rules in order.

Inputs: index (required), patterns (required). Returns: result

start_stop_scheduleA

Start (enable) or stop (disable) a schedule.

Args: schedule_index: Schedule index (0-based). is_start: True to enable the schedule, False to disable it.

Inputs: is_start (required), schedule_index (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 15 tools

    Disambiguation5/5

    Each tool targets a distinct resource (storage, repository, schedule, job) and a unique action (create, delete, get, set, list). The two status tools are clearly separated by their focus: schedule status vs backup status.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in lower_snake_case (e.g., create_storage, get_filters, delete_job). Verbs are specific and predictable, making the naming uniform and easy to anticipate.

    Tool Count5/5

    15 tools is well-scoped for a backup management server, covering the core resources without unnecessary bloat. Each tool has a clear role in the lifecycle of storages, repositories, schedules, and jobs.

    Completeness5/5

    The tool set provides comprehensive CRUD-like coverage for storages and repositories, full schedule and job lifecycle management, plus filter configuration and status monitoring. No critical operations are missing; any workaround is only for convenience, not necessity.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      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.
      2
      -
    • A
      license
      A
      quality
      B
      maintenance
      MCP server that reads Duplicacy backup metrics from a Prometheus exporter and exposes them to LLMs for monitoring backup status, progress, and health.
      6
      391 npm
      3
      GPL 3.0
    • A
      license
      B
      quality
      D
      maintenance
      MCP server for Duplicati backup management. Enables checking status, running backups, viewing logs, and controlling the scheduler.
      21
      MIT