pbs-mcp
MCP server for Proxmox Backup Server. Exposes datastore status, snapshot inventory, garbage collection, verify, and prune over the PBS REST API as 13 LLM-callable tools.
README
pbs-mcp
MCP server for Proxmox Backup Server. Exposes datastore status, snapshot inventory, garbage collection, verify, and prune over the PBS REST API as 13 LLM-callable tools. Designed for the Model Context Protocol.
Türkçe için → README.tr.md
Why
PBS already has a polished web UI. This server is for the cases where the UI isn't where you are — answering "is anything broken?" from a chat assistant, or wiring PBS state into a homelab agent that schedules verifies and prunes based on real conditions.
Tools (13)
| # | Tool | Mode | Notes |
|---|---|---|---|
| 1 | pbs_list_datastores |
read | Configured datastores + schedules |
| 2 | pbs_datastore_status |
read | total / used / available bytes |
| 3 | pbs_list_groups |
read | Per-group snapshot count, owner, corruption flag |
| 4 | pbs_list_snapshots |
read | Size, files, last verify state, protected flag |
| 5 | pbs_get_task_status |
read | UPID → running / OK / error |
| 6 | pbs_get_task_log |
read | Tail or paginate a task log |
| 7 | pbs_list_tasks |
read | Recent tasks, optional filters |
| 8 | pbs_gc_status |
read | Last GC stats: bytes referenced, pending, removed |
| 9 | pbs_run_gc |
write | Trigger GC, returns UPID (async) |
| 10 | pbs_run_verify |
write | Trigger verify, optional snapshot scope |
| 11 | pbs_prune_dry_run |
read | Preview which snapshots a retention policy would drop |
| 12 | pbs_prune |
write | Apply retention policy |
| 13 | pbs_forget_snapshot |
write | Delete one snapshot (corrupt cleanup) |
Write tools require both PBS_ALLOW_WRITE=true in the environment and
confirm=true in the call itself. Restore is intentionally out of scope —
the standard proxmox-mcp already handles restore from PBS via archive=
on the Proxmox VE side.
Setup
1. Create an API token in PBS
In a shell on the PBS host (pct enter 205 from Proxmox if PBS lives in
an LXC, otherwise just SSH):
# Generate a token under root@pam
proxmox-backup-manager user generate-token root@pam mcp
# Grant it admin on your datastore
proxmox-backup-manager acl update /datastore/<your-datastore> \
DatastoreAdmin --auth-id 'root@pam!mcp'
The generate-token output includes a value field — that's the secret,
shown only once. Save it.
Why DatastoreAdmin? PBS performs an owner check on prune. Either you give the token DatastoreAdmin (this), or you keep moving backup ownership with
change-ownerafter every push. Admin scope is simpler and stays inside one datastore.
2. Configure the MCP server
git clone https://github.com/ahmetem/pbs-mcp.git
cd pbs-mcp
cp .env.example .env
# Edit .env: fill in PBS_HOST, PBS_TOKEN_ID, PBS_TOKEN_SECRET
pip install -e .
3. Register with your MCP client
For Claude Desktop, add to claude_desktop_config.json:
{
"mcpServers": {
"pbs": {
"command": "python",
"args": ["/absolute/path/to/pbs-mcp/pbs_mcp.py"]
}
}
}
Restart the client. The pbs_* tools should appear.
Safety model
- Read-only by default. Out of the box
PBS_ALLOW_WRITE=false, so every state-changing tool refuses regardless ofconfirm. - Two-key requirement on writes.
PBS_ALLOW_WRITE=trueopens the door; each call still needsconfirm=true. Two independent toggles, two intentional actions. - Async tasks return UPIDs, not results.
run_gcandrun_verifykick off work and hand back a UPID immediately. Poll withget_task_status. This prevents the MCP request from blocking for hours. - Token scoped to one datastore. ACLs live at
/datastore/<name>, not at/. A leaked token can't read PBS user lists or remote sync configs.
Notes / gotchas
- First-call cache lag: PBS caches ACLs for a few seconds. If you just granted permissions and the next call returns "permission check failed", wait 3 seconds and retry.
- Token vs user permissions: PBS API tokens get the intersection of the
parent user's ACLs and the token's ACLs. With
root@pam!mcpthe parent is unrestricted, so only the token's ACL matters in practice. - Self-signed cert: PBS ships with a self-signed cert. The default
PBS_VERIFY_TLS=falseis fine for a LAN setup. For real CAs, setPBS_VERIFY_TLS=trueandPBS_CA_BUNDLEto a PEM file. - UPIDs are tied to their creator: a UPID created by a now-deleted user becomes unreadable. Don't recycle PBS users while there are pending tasks.
License
GPL-3.0-or-later. See LICENSE.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。