# Zotero

> Use this tool when you need to integrate your local research library with an AI interface, such as Claude's Desktop, to access and analyze your collected literature and notes. It solves problems of data accessibility and AI-assisted research by providing functions for listing collections, searching, and retrieving item details from your Zotero library. With inputs including library searches and item requests, and outputs including item details and collection lists, use Zotero MCP when you want to leverage AI assistance in exploring your personal research collections.

Canonical page: https://skillsregistry.net/skills/gyger-zotero  
JSON: https://api.skillsregistry.net/v1/skills/gyger-zotero

## Description

This Zotero MCP connector, developed by Samuel Gyger, integrates local Zotero libraries with Claude's Desktop interface. It utilizes the pyzotero library and Zotero 7's local web API to provide direct read access to users' research collections. The connector offers functions for listing collections, retrieving item details, searching the library, and fetching recent additions. Built with Python 3.10+ and the FastMCP framework, it stands out by focusing on local Zotero installations rather than cloud-based alternatives. This implementation is particularly useful for researchers and academics who want to leverage AI assistance in exploring and analyzing their personal Zotero libraries, enabling natural language interactions with their collected literature and notes.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gyger-zotero)
- **Repository:** <https://github.com/gyger/mcp-pyzotero>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gyger-zotero"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gyger-zotero` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gyger-zotero/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt