Zimi MCP Server
Enables AI agents to search, read, and manage offline knowledge from ZIM files (Kiwix archives) with full-text search, language support, and library management.
README
Zimi
A modern experience for your ZIM files.
Kiwix packages the world's knowledge into ZIM files. Zimi makes them feel like the real internet with a rich web UI, fast JSON API, and an MCP server for AI agents. Everything works offline, in your language.
What's in the box
- Cross-source search. Parallel full-text search across all sources with snippets and thumbnails.
- Cross-language navigation. Switch articles between languages and download missing ones.
- Discover. Fresh cards daily: Picture of the Day, On This Day, Quote, Word, Book, Destination, Talk, Comic, Country.
- Bookmarks and history. Feel like you're in a real browser, save your place.
- Kiwix Catalog. Download 1,000+ Kiwix archives across 10 categories with instant language filtering.
- Library management. Auto-updates, password protection, download queue.
- Collections and Favorites. Group sources for easier access and scoped search.
- JSON API. Every feature accessible programmatically with token auth.
- Desktop and mobile. Native macOS and Python apps. Deploy anywhere.
Screenshots
| Homepage | Search Results |
|---|---|
![]() |
![]() |
| Language Switching | Catalog |
|---|---|
![]() |
![]() |
| Article Reader |
|---|
![]() |
Languages
Not an afterthought. Language is deeply integrated into every aspect of Zimi so you can focus on your content and feel at home. Enjoy filtered lists, labeled sources, RTL support and no rock left unturned.
- 10 languages. English, French, German, Spanish, Portuguese, Russian, Chinese, Arabic, Hindi, Hebrew.
Something not right? Open an issue.
Install
macOS
brew tap epheterson/zimi && brew install --cask zimi
Or download from GitHub Releases.
Linux
sudo snap install zimi
Or grab the AppImage.
Docker
docker run -v ./zims:/zims -v ./zimi-config:/config -p 8899:8899 epheterson/zimi
/zims is where ZIM files live. /config persists cache, indexes, and settings. Open http://localhost:8899.
<details> <summary>Docker Compose</summary>
services:
zimi:
image: epheterson/zimi
container_name: zimi
restart: unless-stopped
ports:
- "8899:8899"
volumes:
- ./zims:/zims # ZIM files go here
- ./zimi-config:/config # cache, indexes, settings
</details>
Python
pip install zimi
ZIM_DIR=./zims zimi serve --port 8899
Environment Variables
| Variable | Default | Description |
|---|---|---|
ZIM_DIR |
/zims |
Path to ZIM files (scanned for *.zim on startup) |
ZIMI_DATA_DIR |
/config (Docker) or $ZIM_DIR/.zimi |
Cache, indexes, and settings. Mount separately in Docker. |
ZIMI_MANAGE |
1 |
Library manager. 0 to disable. |
ZIMI_MANAGE_PASSWORD |
(none) | Protect library management |
ZIMI_AUTO_UPDATE |
0 |
Auto-update ZIMs (1 to enable) |
ZIMI_UPDATE_FREQ |
weekly |
daily, weekly, or monthly |
ZIMI_RATE_LIMIT |
60 |
Requests/min/IP. 0 to disable. |
API
| Endpoint | Description |
|---|---|
GET /search?q=...&limit=5&zim=...&fast=1&lang=... |
Full-text search. fast=1 for title matches only. lang filters by language. |
GET /read?zim=...&path=...&max_length=8000 |
Read article as plain text |
GET /suggest?q=...&limit=10&zim=... |
Title autocomplete |
GET /list |
List all sources with metadata |
GET /article-languages?zim=...&path=... |
All languages an article is available in |
GET /catalog?zim=... |
PDF catalog for zimgit ZIMs |
GET /snippet?zim=...&path=... |
Short text snippet |
GET /random?zim=... |
Random article |
GET /collections |
List collections |
POST /collections |
Create/update a collection |
DELETE /collections?name=... |
Delete a collection |
GET /resolve?url=... |
Resolve external URL to ZIM path |
POST /resolve |
Batch resolve: {"urls": [...]} |
GET /health |
Health check with version |
GET /w/<zim>/<path> |
Serve raw ZIM content |
Examples
# Search across all sources
curl "http://localhost:8899/search?q=python+asyncio&limit=5"
# Search in French only
curl "http://localhost:8899/search?q=eau&lang=fr&limit=5"
# Find all languages for an article
curl "http://localhost:8899/article-languages?zim=wikipedia&path=A/Water"
# Read an article
curl "http://localhost:8899/read?zim=wikipedia&path=A/Water_purification"
MCP Server
Zimi includes an MCP server for AI agents.
{
"mcpServers": {
"zimi": {
"command": "python3",
"args": ["-m", "zimi.mcp_server"],
"env": { "ZIM_DIR": "/path/to/zims" }
}
}
}
For Docker on a remote host:
{
"mcpServers": {
"zimi": {
"command": "ssh",
"args": ["your-server", "docker", "exec", "-i", "zimi", "python3", "-m", "zimi.mcp_server"]
}
}
}
Tools: search (with lang filter), read, suggest, list_sources, random, article_languages, read_with_links, deep_search, list_collections, manage_collection, manage_favorites
Contributing
See CONTRIBUTING.md.
License
Built with ❤️ in California by @epheterson and Claude Code.
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。




