What dependencies are required to run the server?
Python and `uvx` (or `pipx`) are needed; alternatively, Docker can be used. For the local API, Zotero desktop must be running with the local API enabled.
@kujenga
基本信息
Model Context Protocol (MCP) server for the Zotero API, in Python
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"zotero-mcp": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"uv",
"run",
"zotero-mcp"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
This project is a Python server that implements the Model Context Protocol (MCP) for Zotero, providing AI assistants with access to your Zotero library. It is designed for researchers and anyone who wants to interact with their personal Zotero collection through AI tools.
Configure the server using environment variables (ZOTERO_LOCAL, ZOTERO_API_KEY, ZOTERO_LIBRARY_ID, ZOTERO_LIBRARY_TYPE) and run it via uvx (or pipx) with your MCP client, such as Claude Desktop. Alternatively, use the provided Docker image with the Zotero Web API. Enable the local Zotero API in the Zotero desktop settings for direct access.
Python and `uvx` (or `pipx`) are needed; alternatively, Docker can be used. For the local API, Zotero desktop must be running with the local API enabled.
It connects either via the local API (Zotero desktop app, no API key required) or through the Zotero Web API (requires an

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Hindsight: Agent Memory That Learns
Open-source MCP to use Blender with any LLM
A search tool helps dev to solve the naming things problem.
评论