AI Skill Hub 推荐使用:Jellyfin MCP 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
Jellyfin MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Jellyfin MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/jaredtrent/jellyfin-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"jellyfin-mcp": {
"command": "npx",
"args": ["-y", "jellyfin-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Jellyfin MCP 执行以下任务... Claude: [自动调用 Jellyfin MCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"jellyfin_mcp": {
"command": "npx",
"args": ["-y", "jellyfin-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
MCP server that connects AI assistants to your Jellyfin media server — 31 tools, 13 live resources, and 18 guided workflows. Search your library, control playback, manage metadata, find subtitles, troubleshoot your server, and more.
Setup · Transport · Options · MCP capabilities · Important notes
Beyond tools, jellyfin-mcp implements several MCP protocol features that compatible clients can use.
Resources — 13 live data endpoints the AI can read without a tool call. These include server info, library lists, active sessions, now-playing, favorites, recently played, and more. Clients that support MCP resources can access these directly for quick lookups. See resources for the full list.
Resource subscriptions — Clients can subscribe to session and content resources for real-time change notifications. Sessions are polled every 10 seconds; content (latest additions, recently played) every 60 seconds. The server only polls when at least one subscription is active.
Prompts — 18 pre-built workflows the AI can invoke for multi-step tasks. See prompts for the full list.
Completions — Prompt arguments and resource template URIs support auto-completion (e.g., genre lists, language codes, item/user/library ID lookups).
Logging — Tool calls emit structured MCP log notifications with timing data back to the client, in addition to stderr logging for local debugging.
jellyfin-mcp --http --addr 0.0.0.0:8080 --http-token your_secret_token ```
The HTTP server also exposes /health (returns {"status":"ok"}) for monitoring and load balancer health checks. Sessions time out after 30 minutes of inactivity.
| Method | Command | Requirements |
|---|---|---|
| Binary | Download from [Releases](https://github.com/jaredtrent/jellyfin-mcp/releases) | None |
| Go install | go install github.com/jaredtrent/jellyfin-mcp@latest | [Go 1.25+](https://go.dev/dl/) |
| Go run | go run github.com/jaredtrent/jellyfin-mcp@latest | [Go 1.25+](https://go.dev/dl/) |
| npx | npx -y @jaredtrent/jellyfin-mcp | npm (linux/x64 only) |
| Docker | docker pull ghcr.io/jaredtrent/jellyfin-mcp | [Docker](https://docs.docker.com/get-docker/) |
<details> <summary>Detailed instructions for each method</summary>
Binary — download and extract:
tar xzf jellyfin-mcp_*.tar.gz (or unzip on Windows)sudo mv jellyfin-mcp /usr/local/bin/jellyfin-mcp --helpGo install — places the binary in $GOPATH/bin (usually ~/go/bin). Make sure that directory is on your PATH, then verify: jellyfin-mcp --help. (GUI clients may not see ~/go/bin — see the Claude Desktop note below.)
Go run — no install step, best for a quick try. go run …@latest re-resolves the latest version and rebuilds on each launch, adding startup latency that can make MCP clients time out; go must also be on the client's PATH. Install the binary for regular use.
npx — bundles a pre-compiled linux/x64 binary. Intended for MetaMCP and other Docker-based MCP gateways. For other platforms, use one of the methods above.
Docker — a multi-arch image (linux/amd64, linux/arm64) published to GHCR. Runs the Streamable HTTP transport by default. See the Docker section below.
</details>
claude mcp add \ -e JELLYFIN_URL=http://YOUR_SERVER:8096 \ -e JELLYFIN_API_KEY=your_api_key \ jellyfin -- jellyfin-mcp
A multi-arch image (linux/amd64, linux/arm64) is published to the GitHub Container Registry: ghcr.io/jaredtrent/jellyfin-mcp. It runs the Streamable HTTP transport by default, serving the MCP endpoint at /mcp and a health check at /health.
docker run -d --name jellyfin-mcp -p 8080:8080 \
-e JELLYFIN_URL=http://YOUR_SERVER:8096 \
-e JELLYFIN_API_KEY=your_api_key \
ghcr.io/jaredtrent/jellyfin-mcp --http --addr 0.0.0.0:8080 --http-token your_secret_token
A bearer token is required when binding a non-localhost address, so always pass --http-token. Point your MCP client at http://<host>:8080/mcp and send Authorization: Bearer your_secret_token.
docker compose — a ready-to-edit docker-compose.yml is included. Set your Jellyfin URL/key and token, then docker compose up -d.
stdio in Docker — for clients that launch the server as a subprocess, override the entrypoint so it runs with no arguments:
docker run -i --rm \
-e JELLYFIN_URL=http://YOUR_SERVER:8096 \
-e JELLYFIN_API_KEY=your_api_key \
--entrypoint /usr/local/bin/jellyfin-mcp \
ghcr.io/jaredtrent/jellyfin-mcp
Image tags: latest (latest build from main), the full version from release tags (e.g. 2026.603.1), and MAJOR.MINOR.
```sh
| Variable | Required | Description |
|---|---|---|
JELLYFIN_API_KEY | Yes | API key from your Jellyfin dashboard |
JELLYFIN_URL | No | Server URL — e.g. http://YOUR_SERVER:8096, or https://YOUR_SERVER:8920 if HTTPS is enabled. Defaults to a placeholder, so set this. |
JELLYFIN_USER_ID | No | User ID — auto-detected from the API key if not set |
高质量的开源MCP服务器
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,Jellyfin MCP 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | jellyfin-mcp |
| 原始描述 | 开源MCP工具:A Jellyfin MCP server。⭐16 · Go |
| Topics | mcpjellyfingo |
| GitHub | https://github.com/jaredtrent/jellyfin-mcp |
| License | MIT |
| 语言 | Go |
收录时间:2026-06-05 · 更新时间:2026-06-06 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端