Zotero
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/gyger/mcp-pyzotero
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Zotero from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.