qbittorrent-mcp

qbittorrent-mcp

MCP server exposing qBittorrent's WebUI API v2 as tools, enabling LLMs to manage torrents, categories, tags, RSS feeds, search plugins, and application settings.

Category
访问服务器

README

qbittorrent-mcp

Part of the arr-mcps collection. MCP server exposing qBittorrent's WebUI API v2 (qBittorrent >= 5.0) as tools, so an LLM can manage your torrents: list, inspect properties/trackers/files, add/pause/resume/delete torrents, manage categories, tags, RSS feeds and search plugins, and tweak application settings.

Built with FastMCP.

Enabling the API on your qBittorrent server

The WebUI API is enabled by default with the WebUI. You need WebUI access enabled (Tools > Preferences > WebUI) and one of two auth methods:

  • API key (qBittorrent >= v5.2.0 / WebAPI v2.14.1): generate one in Preferences > WebUI > API Key (format qbt_<28 chars>). This is the recommended, stateless option.
  • Username/password: the WebUI login you'd use in the browser. Works on all versions.

Install

Download a wheel from the latest release and install it as a uv tool (no repo checkout needed):

uv tool install qbittorrent_mcp-*.whl

This puts a qbittorrent-mcp command on your PATH. Register it with Claude Code:

claude mcp add qbittorrent \
  --env QBITTORRENT_URL=http://localhost:8080 \
  --env QBITTORRENT_API_KEY=<key> \
  -- qbittorrent-mcp

Or with username/password:

claude mcp add qbittorrent \
  --env QBITTORRENT_URL=http://localhost:8080 \
  --env QBITTORRENT_USERNAME=admin \
  --env QBITTORRENT_PASSWORD=<password> \
  -- qbittorrent-mcp

From source

uv sync
cp .env.example .env   # fill in QBITTORRENT_URL and an auth method
claude mcp add qbittorrent \
  --env QBITTORRENT_URL=http://localhost:8080 \
  --env QBITTORRENT_API_KEY=<key> \
  -- uv run --directory /path/to/qbittorrent-mcp qbittorrent-mcp

Config

Env var Required Default
QBITTORRENT_URL yes -
QBITTORRENT_API_KEY one of* none (preferred)
QBITTORRENT_USERNAME one of* none (fall-back)
QBITTORRENT_PASSWORD one of* none (fall-back)

* You must set either QBITTORRENT_API_KEY or both QBITTORRENT_USERNAME and QBITTORRENT_PASSWORD. If QBITTORRENT_API_KEY is set it wins; otherwise the server logs in with the username/password on first use and reuses the session cookie, re-authenticating automatically if it expires.

Tools

10 resource-scoped tools, each covering multiple qBittorrent WebUI API v2 endpoints (90 total) via an operation parameter. Call a tool with operation set to one of its listed operations and an arguments dict matching that operation's parameters — the tool's own description (visible to your MCP client) lists every operation, its signature, and a one-line doc. This keeps the full API surface available while costing a fraction of the context budget of registering all 90 endpoints as separate tools.

Tool Operations Kind
qbittorrent_torrents 22 reads + writes
qbittorrent_torrent_limits 14 reads + writes
qbittorrent_rss 12 reads + writes
qbittorrent_categories_tags 10 reads + writes
qbittorrent_search 10 reads + writes
qbittorrent_application 9 reads + writes
qbittorrent_transfer 8 reads + writes
qbittorrent_log 2 read-only
qbittorrent_sync 2 read-only
qbittorrent_auth 1 reads + writes

Example: qbittorrent_torrents(operation="qbittorrent_torrents_pause", arguments={"hashes": "abc123"}). Endpoint-level naming (qbittorrent_<verb>_<resource>) is preserved as the operation value, so the full endpoint list is still discoverable from each group tool's description at runtime.

Development

make help  # list all commands
Command Does
make sync uv sync
make test Offline tests - one per endpoint, mocked HTTP
make test-integration Tests against the live instance (needs QBITTORRENT_URL + auth env)
make build Build wheel + sdist into dist/
make bump-patch / bump-minor / bump-major Bump the version in pyproject.toml + uv.lock
make clean Remove build artifacts

The release workflow (.github/workflows/release.yml) builds and publishes to Releases whenever a v* tag is pushed - so the usual flow is make bump-patch, commit, then tag and push.

The integration suite is read-only and never modifies your qBittorrent instance.

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