shiori-mcp
Enables interaction with Shiori, a self-hosted bookmark and read-it-later manager, for managing bookmarks and tags.
README
Shiori MCP
<p align="center"> <a href="https://buymeacoffee.com/rusty4" target="_blank"> <img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="50"> </a> </p>
<!-- mcp-name: io.github.rusty4444/shiori-mcp -->
A Model Context Protocol (MCP) server for Shiori, the self-hosted bookmark and read-it-later manager.
Capabilities
- Verify Shiori connectivity and authentication
- List bookmarks
- Search bookmarks by title, URL, excerpt, and tag
- Get one bookmark by id or exact URL from the bookmark list
- Add bookmarks with Shiori's required tag-object format
- Update bookmarks via either a full-bookmark payload or common field parameters
- Delete bookmarks by id list
- List tags and bookmark counts
- Rename tags
- List accounts visible to the authenticated session
Installation
pipx install git+https://github.com/rusty4444/shiori-mcp.git
Or from a checkout:
python -m venv .venv
source .venv/bin/activate
pip install -e .
Configuration
| Variable | Required | Description |
|---|---|---|
SHIORI_BASE_URL |
Yes | Base URL of the Shiori instance, e.g. https://shiori.example.com |
SHIORI_SESSION_ID |
Optional | Existing Shiori session id; skips login if provided |
SHIORI_USERNAME |
Required unless session id is set | Shiori username |
SHIORI_PASSWORD |
Required unless session id is set | Shiori password |
SHIORI_TIMEOUT |
No | HTTP timeout in seconds, default 20 |
MCP client config
{
"mcpServers": {
"shiori": {
"command": "shiori-mcp",
"env": {
"SHIORI_BASE_URL": "https://shiori.example.com",
"SHIORI_USERNAME": "your-username",
"SHIORI_PASSWORD": "your-password"
}
}
}
}
Tools
| Tool | Purpose |
|---|---|
shiori_health_check |
Verify API connectivity/authentication |
shiori_list_bookmarks |
List bookmarks with client-side limit/offset |
shiori_search_bookmarks |
Search bookmarks by text and/or tag |
shiori_get_bookmark |
Get one bookmark by id from the bookmark list |
shiori_get_bookmark_by_url |
Get one bookmark by exact URL |
shiori_add_bookmark |
Add a bookmark with optional tags/archive/public flags |
shiori_update_bookmark |
Update a bookmark using full Shiori bookmark JSON |
shiori_update_bookmark_fields |
Update common fields without manually constructing full JSON |
shiori_delete_bookmark |
Delete one bookmark id |
shiori_delete_bookmarks |
Delete bookmark ids from a JSON array |
shiori_list_tags |
List tags and bookmark counts |
shiori_rename_tag |
Rename a tag |
shiori_list_accounts |
List accounts visible to this session |
Development and validation
python -m venv .venv
source .venv/bin/activate
pip install -e '.[dev]'
ruff check .
pytest
python scripts/live_docs_test.py
live_docs_test.py validates Shiori public API documentation and repository pages without credentials. Authenticated read/write API behaviours are covered with mocked HTTP tests.
API note
This server targets Shiori's documented legacy API under /api/* because the new API v1 is still documented as in development and self-documented at /swagger/index.html on running instances.
Safety
The write-capable tools mutate a Shiori bookmark database. Keep credentials in environment variables or a secret manager, never in source control.
This project was developed with the assistance of AI tools.
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。