[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Zotero API and MCP server

> Zotero has a public Web API v3 with read and write access (checked 16 Oct 2026). You create a key in your zotero.org account settings and send it with each request. The API covers items, collections, tags, notes and exports, but Zotero ships no MCP server, so your agent has to be wired to the API by hand.

Reference manager for researchers and students: a library of papers and books with collections, tags, notes and PDF annotations, synced between the desktop app and zotero.org.

## What is the Zotero API?

Cotlet's Zotero API exposes 11 endpoints for your own Zotero account: list libraries, search items, get item, list collections, get annotations, export citations, add item by identifier, create collection, add items to collection, add tags and create note. The list_libraries endpoint returns my Library and the group libraries your account belongs to, with their IDs. Each endpoint takes simple JSON inputs like library, collection_key or item_keys and works both as an operation of the zotero_read or zotero_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Productivity & teams](https://cotlet.dev/integrations/category/productivity-teams.md)
- **Endpoints:** 11 (6 read, 5 write)
- **Updated:** 2026-10-18

Zotero has a public Web API v3 with read and write access (checked 16 Oct 2026). Cotlet is a hosted MCP server and REST API for Zotero with 11 endpoints (6 read, 5 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Zotero have an official API?

Zotero has a public Web API v3 with read and write access (checked 16 Oct 2026). You create a key in your zotero.org account settings and send it with each request. The API covers items, collections, tags, notes and exports, but Zotero ships no MCP server, so your agent has to be wired to the API by hand.

| Task | Zotero official | Cotlet |
|---|---|---|
| Search the library | Yes: Quick search over titles and creators, optional full text, filters by tag and item type | Yes |
| Read items, collections and tags | Yes | Yes |
| Add an item by DOI | Partly: The API writes items from metadata you supply; Add Item by Identifier is a desktop app button | Yes |
| Create collections and add items to them | Yes: Items join a collection through their own collections property | Yes |
| Create notes | Yes: A note is a child item when parentItem is set | Yes |
| Get PDF annotations | Partly: The docs describe children of items and full text of attachments, not annotation items | Yes |
| Add tags to items | Yes | Yes |
| Export citations | Yes: BibTeX, BibLaTeX, RIS, CSL JSON and formatted bibliographies | Yes |

Sources: [Zotero Web API v3: basics](https://www.zotero.org/support/dev/web_api/v3/basics), [Zotero Web API v3: write requests](https://www.zotero.org/support/dev/web_api/v3/write_requests), [Zotero Web API v3: full-text content](https://www.zotero.org/support/dev/web_api/v3/fulltext_content), [Zotero: adding items to Zotero](https://www.zotero.org/support/adding_items_to_zotero)

## For AI agents

```text
Zotero has a public Web API v3 with read and write access (checked 16 Oct 2026). You create a key in your zotero.org account settings and send it with each request. The API covers items, collections, tags, notes and exports, but Zotero ships no MCP server, so your agent has to be wired to the API by hand.
Cotlet provides a hosted MCP server and REST API for Zotero: 11 tools (6 read, 5 write).
Access       Sign up at https://cotlet.dev/app/signup?app=zotero, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    zotero_read, zotero_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/zotero, each operation at its own route, e.g. POST /api/v1/zotero/item-by-identifiers
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
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
Markdown     https://cotlet.dev/integrations/zotero-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=zotero, requests Zotero in the Cotlet console and creates an API key there.
2. The user signs in to Zotero once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Zotero for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Zotero server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Zotero MCP server instead.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Zotero in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Zotero only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Zotero login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Zotero's terms; Cotlet is not affiliated with Zotero.
```

## What can an AI agent do in Zotero?

Cotlet is best for researchers and students who keep their reading in Zotero and want an AI agent to add papers, sort collections, export BibTeX and write notes without running or fixing a server.

- **[Add papers to your library from a list of DOIs](https://cotlet.dev/integrations/zotero-api-mcp-server/add-papers-by-doi.md)** (runs: weekly): "Add these DOIs to my Zotero library and put them in the collection "Thesis: related work". Tell me which ones Zotero could not find." → `search_items`, `add_item_by_identifier`, `add_items_to_collection`
- **[Export a Zotero collection as BibTeX or a bibliography](https://cotlet.dev/integrations/zotero-api-mcp-server/export-collection-bibtex.md)** (runs: weekly): "Export my collection "Thesis: related work" as BibTeX and save it as references.bib. Tell me how many entries it has." → `list_collections`, `export_citations`
- **[Turn PDF highlights into a literature note](https://cotlet.dev/integrations/zotero-api-mcp-server/pdf-annotations-to-note.md)** (runs: weekly): "Find the Zotero item "Sparse attention for long documents", read its PDF annotations and write one literature note on it with the quotes grouped by color and the page of each." → `search_items`, `get_annotations`, `create_note`
- **Tag and file new papers into collections** (runs: weekly): "Look at items in my Zotero library that are in no collection. Tag each by topic and add it to the collection that fits; leave the ones you are unsure about and list them." → `search_items`, `add_tags`, `add_items_to_collection`
- **Send a weekly digest of new library items** (runs: weekly): "Every Friday, list the items I added to Zotero in the last 7 days with title, authors and collection, and write me a five-line summary." → `search_items`, `get_item`

## Can Zotero automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Zotero connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to add papers to your library from a list of dois, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/zotero/items/search. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/zotero/items/search with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 11 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Zotero.

### list_libraries

My Library and the group libraries your account belongs to, with their IDs. Access: read. REST: `GET /api/v1/zotero/libraries`. MCP: `zotero_read → list_libraries`.

No parameters.

Returns your personal library first, then each group library with its ID and name. Use the ID as the library parameter of the other read tools. The write tools work on My Library only.

Example response:

```json
{
  "libraries": [
    {
      "library": "me",
      "name": "My Library",
      "type": "personal"
    },
    {
      "library": "4455821",
      "name": "Reading group 2026",
      "type": "group"
    }
  ]
}
```

### search_items

Items in the library matching a phrase, tag, item type or collection, with title, creators, year and tags. Access: read. REST: `GET /api/v1/zotero/items/search`. MCP: `zotero_read → search_items`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `library` | string | no | 'me' for My Library (default) or a group library ID from list_libraries. |
| `query` | string | no | Phrase to find in titles and creators. |
| `full_text` | boolean | no | true also searches the text of attachments. |
| `tag` | string | no | Only items with this tag. |
| `item_type` | string | no | Only this item type, e.g. 'journalArticle' or 'book'. |
| `collection_key` | string | no | Collection key from list_collections. |
| `unfiled` | boolean | no | true lists only items in no collection. |
| `added_since` | datetime | no | Only items added after this time. |
| `limit` | integer | no | Maximum number of items to return. |
| `cursor` | string | no | Next page cursor from the previous call. |

Searches titles and creators by default; set full_text to include the text of attachments. Filter by tag, item type or collection, or show only items in no collection. Results are items with their keys; use get_item for the fields and notes of one item.

Example response:

```json
{
  "items": [
    {
      "item_key": "H6R2VB5D",
      "title": "Sparse attention for long documents",
      "item_type": "journalArticle",
      "creators": [
        "Lee, M.",
        "Okafor, T."
      ],
      "year": 2025,
      "tags": [
        "transformers"
      ],
      "collections": [
        "C4T8WZ2N"
      ]
    },
    {
      "item_key": "N9Q4XA7E",
      "title": "A survey of retrieval for question answering",
      "item_type": "journalArticle",
      "creators": [
        "Novak, P."
      ],
      "year": 2024,
      "tags": [],
      "collections": []
    }
  ],
  "total": 2,
  "next_cursor": null
}
```

### get_item

One item with all its fields, tags, collections and child notes. Access: read. REST: `GET /api/v1/zotero/item`. MCP: `zotero_read → get_item`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `library` | string | no | 'me' for My Library (default) or a group library ID from list_libraries. |
| `item_key` | string | yes | Item key from search_items, 8 characters. |

Returns the full metadata of one item as Zotero stores it, the keys of the collections it is in, its tags, and the child notes with their text. PDF attachments are listed by name, not downloaded.

Example response:

```json
{
  "item_key": "H6R2VB5D",
  "item_type": "journalArticle",
  "title": "Sparse attention for long documents",
  "creators": [
    "Lee, M.",
    "Okafor, T."
  ],
  "date": "2025",
  "doi": "10.1234/example.2026.001",
  "tags": [
    "transformers"
  ],
  "collections": [
    "C4T8WZ2N"
  ],
  "notes": [
    {
      "note_key": "T3P6YK8R",
      "text": "Read in October, check the evaluation setup."
    }
  ],
  "attachments": [
    "Lee and Okafor - 2025 - Sparse attention for long documents.pdf"
  ]
}
```

### list_collections

Collections and subcollections of the library with their keys and item counts. Access: read. REST: `GET /api/v1/zotero/collections`. MCP: `zotero_read → list_collections`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `library` | string | no | 'me' for My Library (default) or a group library ID from list_libraries. |

Returns the collection tree with each key, its parent and the number of items directly in it. Collection names are not unique in Zotero, so use the key and the parent to tell two collections apart.

Example response:

```json
{
  "collections": [
    {
      "collection_key": "C4T8WZ2N",
      "name": "Thesis: related work",
      "parent": null,
      "item_count": 2
    },
    {
      "collection_key": "M2D7FQ4S",
      "name": "Chapter 2",
      "parent": "C4T8WZ2N",
      "item_count": 0
    }
  ]
}
```

### get_annotations

Highlights and comments made in the PDFs of an item, with color and page. Access: read. REST: `GET /api/v1/zotero/annotations`. MCP: `zotero_read → get_annotations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `library` | string | no | 'me' for My Library (default) or a group library ID from list_libraries. |
| `item_key` | string | yes | Item key from search_items, 8 characters. |

Returns the annotations of every PDF attached to the item, in page order, each with its text, comment, color and page. Items without a PDF or without annotations return an empty list. It reads annotations only and never changes the PDF.

Example response:

```json
{
  "item_key": "H6R2VB5D",
  "annotations": [
    {
      "type": "highlight",
      "color": "yellow",
      "page": 4,
      "text": "Attention cost grows linearly with window size.",
      "comment": ""
    },
    {
      "type": "highlight",
      "color": "red",
      "page": 12,
      "text": "Evaluation uses one dataset.",
      "comment": "Check the appendix."
    }
  ]
}
```

### export_citations

Items or a whole collection as BibTeX, BibLaTeX, RIS, CSL JSON or a formatted bibliography. Access: read. REST: `GET /api/v1/zotero/citations/export`. MCP: `zotero_read → export_citations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `library` | string | no | 'me' for My Library (default) or a group library ID from list_libraries. |
| `item_keys` | string[] | no | Items to export. Use this or collection_key. |
| `collection_key` | string | no | Collection key from list_collections. |
| `format` | string | yes | One of 'bibtex', 'biblatex', 'ris', 'csljson' or 'bib' (formatted bibliography). |
| `style` | string | no | Citation style for format 'bib', e.g. 'apa'. |

Exports the items you name, or every item of a collection, in the format you choose. For a bibliography, pass a citation style; otherwise Zotero uses its default. The response holds the text and the number of entries, so you can check nothing was cut.

Example response:

```json
{
  "format": "bibtex",
  "item_count": 2,
  "content": "@article{lee2025sparse,\n  title = {Sparse attention for long documents},\n  author = {Lee, M. and Okafor, T.},\n  year = {2025}\n}\n\n@article{novak2024survey,\n  title = {A survey of retrieval for question answering},\n  author = {Novak, P.},\n  year = {2024}\n}"
}
```

### add_item_by_identifier

Add papers or books to My Library from DOIs, ISBNs, PubMed IDs, arXiv IDs or ADS Bibcodes. Access: write. REST: `POST /api/v1/zotero/item-by-identifiers`. MCP: `zotero_write → add_item_by_identifier`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `identifiers` | string[] | yes | DOIs, ISBNs, PubMed IDs, arXiv IDs or ADS Bibcodes. |
| `collection_key` | string | no | Put the new items in this collection. |

Looks up each identifier the way Add Item by Identifier does in the Zotero app and adds one item per match, into the collection you name. Identifiers Zotero cannot resolve come back in not_found and add nothing. It writes to your own library only and runs without asking first: nobody else sees the items and you can remove them in Zotero with Move Item(s) to Trash….

Example response:

```json
{
  "requested": 3,
  "created": [
    {
      "item_key": "H6R2VB5D",
      "title": "Sparse attention for long documents",
      "identifier": "10.1234/example.2026.001"
    },
    {
      "item_key": "N9Q4XA7E",
      "title": "A survey of retrieval for question answering",
      "identifier": "10.1234/example.2026.002"
    }
  ],
  "not_found": [
    "10.9999/broken.2026.7"
  ],
  "collection_key": "C4T8WZ2N"
}
```

### create_collection

Create a collection or a subcollection in My Library. Access: write. REST: `POST /api/v1/zotero/collections`. MCP: `zotero_write → create_collection`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `name` | string | yes | Collection name. |
| `parent_collection_key` | string | no | Create it under this collection. |

Creates a collection with the name you give, at the top level or under a parent collection. Two collections may share a name, so the call returns the new key. It reaches nobody and runs without asking first; delete the collection in Zotero if you do not want it.

Example response:

```json
{
  "collection_key": "M2D7FQ4S",
  "name": "Chapter 2",
  "parent": "C4T8WZ2N"
}
```

### add_items_to_collection

Add items to a collection; they stay in the collections they are already in. Access: write. REST: `POST /api/v1/zotero/items-to-collections`. MCP: `zotero_write → add_items_to_collection`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `collection_key` | string | yes | Collection key from list_collections. |
| `item_keys` | string[] | yes | Items to add. |

Adds the items to the collection the way dragging them onto it does, so they keep their other collections. It reaches nobody and runs without asking first; Remove Item(s) from Collection… in Zotero undoes it.

Example response:

```json
{
  "collection_key": "C4T8WZ2N",
  "added": [
    "H6R2VB5D",
    "N9Q4XA7E"
  ],
  "already_in_collection": []
}
```

### add_tags

Add tags to one or more items. Access: write. REST: `POST /api/v1/zotero/tags`. MCP: `zotero_write → add_tags`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `item_keys` | string[] | yes | Items to tag. |
| `tags` | string[] | yes | Tags to add. |

Adds the tags to each item and keeps the tags it already has. It reaches nobody and runs without asking first; removing a tag is a click on the minus button next to it in Zotero.

Example response:

```json
{
  "updated": [
    "H6R2VB5D",
    "N9Q4XA7E"
  ],
  "tags_added": [
    "transformers",
    "to read"
  ]
}
```

### create_note

Add a note to an item, or a standalone note. Access: write. REST: `POST /api/v1/zotero/notes`. MCP: `zotero_write → create_note`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `parent_item_key` | string | no | Attach the note to this item. Omit for a standalone note. |
| `note` | string | yes | Note text. |
| `collection_key` | string | no | For a standalone note: put it in this collection. |

With parent_item_key the note becomes a child note of that item; without it, a standalone note appears next to the other items. It never changes the item or its PDF, reaches nobody and runs without asking first. Move Item(s) to Trash… in Zotero removes it.

Example response:

```json
{
  "note_key": "T3P6YK8R",
  "parent_item_key": "H6R2VB5D",
  "created_at": "2026-10-16T09:00:00+02:00"
}
```

## How do I connect Zotero to Claude Code, Codex or Cursor?

Connecting Zotero takes three steps: sign up, sign in to Zotero once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect Zotero to your agent.

1. **Create an account** Sign up and add Zotero in the console. Your API key is there too.

2. **Sign in to Zotero in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Zotero there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   Claude Code:

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

   Cursor:

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

   Codex:

```
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

4. **Ask your agent** Ask in plain words. Your agent finds the Zotero tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

```
Add these DOIs to my Zotero library and put them in the collection "Thesis: related work". Tell me which ones Zotero could not find.
```

### Call Zotero from your scripts.

1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

```
export COTLET_API_KEY="cotlet_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/zotero with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.

```
curl -X POST https://cotlet.dev/api/v1/zotero/item-by-identifiers \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"identifiers":["10.1234/example.2026.001","10.1234/example.2026.002","10.9999/broken.2026.7"],"collection_key":"C4T8WZ2N"}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "requested": 3,
  "created": [
    {
      "item_key": "H6R2VB5D",
      "title": "Sparse attention for long documents",
      "identifier": "10.1234/example.2026.001"
    },
    {
      "item_key": "N9Q4XA7E",
      "title": "A survey of retrieval for question answering",
      "identifier": "10.1234/example.2026.002"
    }
  ],
  "not_found": [
    "10.9999/broken.2026.7"
  ],
  "collection_key": "C4T8WZ2N"
}
```

## Why use Cotlet for Zotero?

**Built for agents**

- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to Zotero yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.

**Kept working for you**

- We test every integration every 6 hours.
- When Zotero changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Zotero to Cotlet?

Yes. You sign in to Zotero yourself, in your own Cloud Browser, and we never save your password. Your agents only get Zotero once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

- **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### Common concerns

**Who runs Cotlet?**

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

**Is this an official Zotero integration?**

No, Cotlet is independent of Zotero. Zotero's own API is too limited for this work. Cotlet works through your own Zotero account, the way you use Zotero in the browser, so you need no partner approval and no developer setup.

**What about client data and GDPR?**

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

**Can I start with read only?**

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

**Is it reliable?**

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

**How do I stop?**

Press Disable for agents next to Zotero in your console: your agents lose access at once and you stay signed in. Signing out of Zotero in the browser works too, and Reset browser deletes the whole profile.

## Is there a Zotero MCP server on GitHub?

Yes. Community Zotero MCP servers exist on GitHub, usually maintained by one person, and most need Python or the desktop app running on your computer. You install one, create a Zotero API key, and fix it yourself when Zotero or your Python setup changes. Wiring the Web API into your own script means the same keys and hosting. Cotlet hosts the same tools for you, and our team keeps them working.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, install Python, create a Zotero API key, add the server to each MCP client | Sign up, sign in to Zotero once, add one MCP server or API key |
| When Zotero changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your Zotero access | An API key in a config file on your computer, readable by any program you run | Signed in inside your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When access expires | Tools fail until you create a new key or restart the desktop app | Your Cloud Browser keeps you signed in; if Zotero logs you out, your agent gets a link to sign in again |
| Upkeep | You update dependencies, handle rate limits and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on and Zotero is open | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |

### Which one fits you

**Pick Cotlet if**

- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Zotero changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off

**Pick an open-source server if**

- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the Zotero API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Zotero API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

| Credits | Price, one time | Calls at 25 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 200 | $5.80 |
| 15,000 | $79 | 600 | $5.27 |
| 32,000 | $149 | 1,280 | $4.66 |
| 60,000 | $249 | 2,400 | $4.15 |

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Zotero account.

- **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to Zotero yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Zotero only after you enable it. When Zotero signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to Zotero, sign out of Zotero in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA.
- **Zotero's terms:** You use your own Zotero account and stay responsible for following Zotero's terms. Cotlet is independent and not affiliated with Zotero. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open Zotero in the console and press Request access. Then you create your API key and connect Zotero there.

**Do I need to be technical?**

No. You sign in to Zotero once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

**Is it safe to connect Zotero to Cotlet?**

Yes. You sign in to Zotero yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Zotero once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

**Is a hosted server safer than a local one? My Zotero sign-in would leave my computer.**

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Zotero cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

**Why does Cotlet send requests instead of clicking in my browser?**

To be fast, Cotlet doesn't click through Zotero's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Zotero sees the same browser and IP you signed in with, and every request is listed in your Background activity.

**What if someone gets my Cotlet API key?**

The key holds no Zotero login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

**Why a signed-in browser and not OAuth, like other integration platforms?**

Zotero offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

**Do I need Zotero Storage or a paid plan?**

No. Cotlet works on your synced library, and data syncing for items, notes, tags and collections is free and unlimited. Zotero Storage matters only for PDF files, where the free quota is 300 MB.

**Can the agent work in group libraries?**

It can read group libraries you belong to with the library parameter. Writes go to My Library only, so nothing an agent adds appears for other members of a group.

**Can my agent post or send messages in Zotero without asking me?**

No. Every call to undefined waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_item_by_identifier, create_collection, add_items_to_collection, add_tags, create_note runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the Zotero API in n8n?**

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/zotero from the HTTP Request node.

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.

## For AI agents: sign your user up

Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed.

1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests
2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them.
3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests.

One call creates the account and sends the access request; we email the user when access is granted.