Model Context Protocol server for Zotero

Created By
kujengaa year ago
Model Context Protocol (MCP) server for the Zotero API, in Python
Overview

what is Zotero MCP?

Zotero MCP is a Model Context Protocol server for the Zotero API, implemented in Python, allowing users to interact with their Zotero libraries programmatically.

how to use Zotero MCP?

To use Zotero MCP, install it by adding the configuration to your mcpServers in Claude Desktop, and set the necessary environment variables. You can then access its features through the MCP Inspector or any compatible MCP client.

key features of Zotero MCP?

  • zotero_search_items: Search for items in your Zotero library using a text query.
  • zotero_item_metadata: Retrieve detailed information about a specific Zotero item.
  • zotero_item_fulltext: Access the full text of a specific Zotero item.

use cases of Zotero MCP?

  1. Automating the retrieval of bibliographic data from Zotero.
  2. Integrating Zotero with other applications for enhanced research workflows.
  3. Facilitating the management of research materials through programmatic access.

FAQ from Zotero MCP?

  • Can Zotero MCP be used with the local Zotero API?

Yes! Zotero MCP supports the local Zotero API for users running Zotero on the same machine.

  • Is there a need for an API key?

An API key is not required for the local API but is necessary for remote access to your Zotero library.

  • How do I run tests for Zotero MCP?

You can run the test suite using the command uv run pytest.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
kujenga
Star
44
Language
Python
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago