Skip to main content
Glama
Zotero MCP server

Zotero MCP server

README.md
# Zotero MCP server

Connect Zotero to ChatGPT, Claude and any AI agent through Cotlet.dev. Search your synced library, read PDF annotations, export citations and add papers or notes. Read your personal and group libraries; writes go to My Library only.

## What you can ask

> Add these DOIs to my Thesis collection.

> Export Chapter 2 as BibTeX.

> Write a literature note from my PDF highlights.

## Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as `COTLET_API_KEY`.

### ChatGPT

Settings → Apps & Connectors → Create, connector URL `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev. No API key needed.

### Claude

Settings > Connectors > Add custom connector, URL `https://cotlet.dev/mcp/v1/connect`, then sign in with Cotlet.dev.

### Claude Code

```bash
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
```

### Cursor

Copy `.cursor/mcp.json` from this repo into your project:

```json
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

## Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Zotero tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

Run the included Python module with Python 3.10 or later:

```bash
python3 zotero_agent.py serve
```

Or with Docker:

```bash
docker build -t zotero-mcp .
docker run -i --rm -e COTLET_API_KEY zotero-mcp
```

Tools: `zotero_guide`, `zotero_status`, `zotero_open`, `zotero_read`, `zotero_click`, `zotero_type`, `zotero_close`. Without `COTLET_API_KEY` a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

## Command line

Python 3.10+, with no third-party runtime dependencies. Clone this repository and run:

```bash
export COTLET_API_KEY="your-key"
python3 zotero_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 zotero_agent.py status    # is Zotero ready in your Cotlet.dev account
python3 zotero_agent.py guide     # Zotero screens and sign-in link
python3 zotero_agent.py read      # open Zotero, read the page, close the browser
python3 zotero_agent.py tools     # list Cotlet.dev tools
python3 zotero_agent.py serve     # start the stdio MCP server (same as no argument)
```

## Questions from Zotero users

**Which Zotero libraries can my agent use?**

Read My Library and group libraries your account belongs to. Writes go to My Library only. Use your Zotero account with sync enabled.

**Can it change my PDF files?**

The annotations operation reads highlights and comments without changing the PDF. Notes are separate Zotero items.

**Is this affiliated with Zotero?**

No. Cotlet.dev is an unofficial integration, independent and not affiliated with Zotero.

## Learn more

- [Zotero integration and hosted tools](https://cotlet.dev/integrations/zotero-api-mcp-server)

---

More: https://cotlet.dev/integrations/zotero-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=zotero

Request access: https://cotlet.dev/signup?app=zotero&utm_source=github&utm_medium=readme&utm_campaign=zotero

## Workflows on the hosted integration

The live integration page documents these 11 operations:

- `list_libraries`
- `search_items`
- `get_item`
- `list_collections`
- `get_annotations`
- `export_citations`
- `add_item_by_identifier`
- `create_collection`
- `add_items_to_collection`
- `add_tags`
- `create_note`

The local stdio adapter exposes seven browser helpers listed above. These helpers forward to Cotlet.dev; the workflow operations are documented on the hosted integration page.