Audiobookshelf MCP Server

Audiobookshelf MCP Server

A Model Context Protocol server that gives AI assistants access to your self-hosted Audiobookshelf library, enabling queries about current listening, searching, and browsing.

Category
访问服务器

README

Audiobookshelf MCP Server

Go Go Report Card MCP Registry

A Model Context Protocol server for Audiobookshelf - gives AI assistants access to your self-hosted audiobook and podcast library.

MCP Registry name: mcp-name: io.github.sierikov/audiobookshelf-mcp

What can it do?

Ask your AI assistant things like:

  • "What am I currently listening to?"
  • "Search for Dune in my library"
  • "What are my listening stats?"
  • "What did I listen to recently?"
  • "How far am I in Katabasis?"
  • "What libraries do I have?"

Tools

Tool Description Toolset
list_libraries List all libraries libraries
search_library Search by title, author, or narrator libraries
list_library_items List items with pagination libraries
get_item Get detailed info about an audiobook or podcast items
get_items_in_progress Get currently listening items with progress items
get_listening_stats Total listening time and daily breakdown playback
get_listening_sessions Recent listening sessions playback
get_media_progress Progress for a specific item playback
list_series List all series in a library browse
get_series Get series details with books browse
get_author Get author details with books browse
list_collections List collections in a library browse

Default toolsets: libraries, items, playback. The browse toolset is opt-in via AUDIOBOOKSHELF_TOOLSETS.


Install in Claude Desktop (one-click)

Download the .mcpb bundle for your platform, open it, and Claude Desktop will walk you through setup.

Platform Download
macOS (Apple Silicon) audiobookshelf-mcp-macos-arm64.mcpb
macOS (Intel) audiobookshelf-mcp-macos-amd64.mcpb
Windows audiobookshelf-mcp-windows-amd64.mcpb
Linux x64 audiobookshelf-mcp-linux-amd64.mcpb
Linux arm64 audiobookshelf-mcp-linux-arm64.mcpb

The .mcpb format is currently only supported by Claude Desktop. Other clients use the manual setup below.


Manual setup (all other clients)

1. Get your API token

Audiobookshelf → Settings → Users → your user → API Token

2. Install the binary

go install:

go install github.com/sierikov/audiobookshelf-mcp/cmd/audiobookshelf-mcp@latest

Download and install to /usr/local/bin:

<details> <summary>macOS (Apple Silicon)</summary>

curl -L https://github.com/sierikov/audiobookshelf-mcp/releases/latest/download/audiobookshelf-mcp-macos-arm64 \
  -o /usr/local/bin/audiobookshelf-mcp && chmod +x /usr/local/bin/audiobookshelf-mcp

</details>

<details> <summary>macOS (Intel)</summary>

curl -L https://github.com/sierikov/audiobookshelf-mcp/releases/latest/download/audiobookshelf-mcp-macos-amd64 \
  -o /usr/local/bin/audiobookshelf-mcp && chmod +x /usr/local/bin/audiobookshelf-mcp

</details>

<details> <summary>Linux (x64)</summary>

curl -L https://github.com/sierikov/audiobookshelf-mcp/releases/latest/download/audiobookshelf-mcp-linux-amd64 \
  -o /usr/local/bin/audiobookshelf-mcp && chmod +x /usr/local/bin/audiobookshelf-mcp

</details>

<details> <summary>Linux (arm64)</summary>

curl -L https://github.com/sierikov/audiobookshelf-mcp/releases/latest/download/audiobookshelf-mcp-linux-arm64 \
  -o /usr/local/bin/audiobookshelf-mcp && chmod +x /usr/local/bin/audiobookshelf-mcp

</details>

<details> <summary>Windows</summary>

Download audiobookshelf-mcp-windows-amd64.exe, rename to audiobookshelf-mcp.exe, and place it in a directory on your %PATH% (e.g. C:\Program Files\audiobookshelf-mcp\).

</details>

3. Configure your client

<details> <summary>Claude Code</summary>

claude mcp add audiobookshelf \
  -e AUDIOBOOKSHELF_URL=https://abs.example.com \
  -e AUDIOBOOKSHELF_TOKEN=your-token \
  -- audiobookshelf-mcp

</details>

<details> <summary>Antigravity CLI (formerly Gemini CLI)</summary>

antigravity --add-mcp '{"name":"audiobookshelf","command":"audiobookshelf-mcp","env":{"AUDIOBOOKSHELF_URL":"https://abs.example.com","AUDIOBOOKSHELF_TOKEN":"your-token"}}'

</details>

<details> <summary>OpenCode</summary>

Add to ~/.config/opencode/config.json:

{
  "mcpServers": {
    "audiobookshelf": {
      "type": "stdio",
      "command": "audiobookshelf-mcp",
      "args": [],
      "env": {
        "AUDIOBOOKSHELF_URL": "https://abs.example.com",
        "AUDIOBOOKSHELF_TOKEN": "your-token"
      }
    }
  }
}

</details>


Configuration

Variable Required Default Description
AUDIOBOOKSHELF_URL Yes Your Audiobookshelf server URL
AUDIOBOOKSHELF_TOKEN Yes API token from Settings → Users
AUDIOBOOKSHELF_TOOLSETS No libraries,items,playback Comma-separated toolsets to enable. Use all to enable everything.

Security

All tools are read-only - no writes, no playback control, no user management. The API token is passed via environment variable, never logged or exposed.

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