ZoteroSAFE
MCP server to expose local zotero repository to MCP clients
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A MCP (Model Context Protocol) server to let your MCP clients (e.g. Anthropic Claude App, Goose, possibly vscode Cline too) interact with your local Zotero repository. This server enables programmatic access to your Zotero library, allowing you to search papers, manage notes, and more.
Note: If you don't want to set up API keys, see the SQLite database server option below.
Setup
- Install dependencies:
pip install -e .
- Create a
.envfile in the root directory with your Zotero credentials:
ZOTERO_API_KEY=your_api_key_here ZOTERO_USER_ID=your_user_id_here
You can get your Zotero API key and user ID from Zotero's settings page.
Integration with Anthropic Desktop App
To integrate with the Anthropic Desktop app, add the following configuration to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"zotero-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/Users/swairshah/work/research/zotero-mcp",
"run",
"python",
"-m",
"zotero_mcp.server"
]
}
}
}If this gives an error like
{"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"claude-ai","version":"0.1.0"}},"jsonrpc":"2.0","id":0}
error: unexpected argument '--directory' foundThen use the following config, make sure to do uv venv; source .venv/bin/activate; uv pip install ".[dev]" to make sure the server can be run with all dependencies.
{
"mcpServers": {
"zotero-mcp-server": {
"command": "bash",
"args": [
"-c",
"cd /Users/shahswai/personal/zotero-mcp-server && source .venv/bin/activate && python -m zotero_mcp.server"
]
}
}
}Alternative: Direct SQLite Database Access
If you prefer to bypas
20fec4d6f89aOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add zotero-mcp --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env ZOTERO_API_KEY=${ZOTERO_API_KEY} -- uvx zotero-mcp{
"mcpServers": {
"zotero-mcp": {
"command": "uvx",
"args": [
"zotero-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"ZOTERO_API_KEY": "${ZOTERO_API_KEY}"
}
}
}
}Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_note | write | Add a note to a specific paper. |
get_paper | read | Get details for a specific paper. |
get_paper_notes | read | Get all notes attached to a specific paper. |
get_pdf_content | read | Get the PDF content for a given item. |
search_papers | read | Search through Zotero papers based on tags and/or text. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
20fec4d6f89afull audit observations/trust-audit/mcp-server/swairshah__zotero-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 20fec4d6f89a | SAFE | B | 89 | first audit |
Questions
What is the Zotero MCP server?
MCP server to expose local zotero repository to MCP clients
What tools does Zotero expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Zotero safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Zotero need?
It reads ANTHROPIC_API_KEY and ZOTERO_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (20fec4d6f89a), read on 2026-10-08. The repository is watched and re-audited when it changes.