The Zotero MCP Server integrates with Zotero to provide AI assistants access to your Zotero library via the Model Context Protocol. You can:
Search for items in your library using text queries, with options for query mode (titleCreatorYear or everything) and tags
Retrieve detailed metadata about specific Zotero items using their item keys
Access full text content (like PDF content) of items using their item keys
Provides access to your Zotero library, allowing you to search for items, retrieve detailed metadata, and access the full text contents of PDFs and other documents stored in your Zotero collection.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Zotero MCP Server search for papers about machine learning ethics"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project is a python server that implements the Model Context Protocol (MCP) for Zotero, giving you access to your Zotero library within AI assistants. It is intended to implement a small but maximally useful set of interactions with Zotero for use with MCP clients.
This MCP server provides the following tools:
zotero_search_items: Search for items in your Zotero library using a text query
zotero_item_metadata: Get the complete metadata for a specific Zotero item, covering every populated field grouped into publication details, identifiers, timestamps, and library information
zotero_item_fulltext: Get the full text of a specific Zotero item (i.e. PDF contents)
These can be discovered and accessed through any MCP client or through the MCP Inspector.
Each tool returns formatted text containing relevant information from your Zotero items, and AI assistants such as Claude can use them sequentially, searching for items then retrieving their metadata or text content.
Related MCP server: zotero-assistant-mcp
This server can either run against either a local API offered by the Zotero desktop application) or through the Zotero Web API. The local API can be a bit more responsive, but requires that the Zotero app be running on the same computer with the API enabled. To enable the local API, do the following steps:
Open Zotero and open "Zotero Settings"
Under the "Advanced" tab, check the box that says "Allow other applications on this computer to communicate with Zotero".
To use the Zotero Web API, you'll need to create an API key and find your Library ID (usually your User ID) in your Zotero account settings here: https://www.zotero.org/settings/keys
These are the available configuration options:
ZOTERO_LOCAL=true: Use the local Zotero API (default: false, see note below)
ZOTERO_API_KEY: Your Zotero API key (not required for the local API)
ZOTERO_LIBRARY_ID: Your Zotero library ID (your user ID for user libraries, not required for the local API)
ZOTERO_LIBRARY_TYPE: The type of library (user or group, default: user)
uvx with Local Zotero APITo use this with Claude Desktop and a direct python install with uvx, add the following to the mcpServers configuration:
{
"mcpServers": {
"zotero": {
"command": "uvx",
"args": ["zotero-mcp@latest"],
"env": {
"ZOTERO_LOCAL": "true",
"ZOTERO_API_KEY": "",
"ZOTERO_LIBRARY_ID": ""
}
}
}
}The @latest specifier is optional and will pull the latest version when new ones are available. If you don't have uvx installed you can use pipx run instead, or clone this repository locally and use the instructions in Development below.
If you want to run this MCP server in a Docker container, you can use the following configuration, inserting your API key and library ID:
{
"mcpServers": {
"zotero": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "ZOTERO_API_KEY=PLACEHOLDER",
"-e", "ZOTERO_LIBRARY_ID=PLACEHOLDER",
"ghcr.io/kujenga/zotero-mcp:main"
],
}
}
}To update to a newer version, run docker pull ghcr.io/kujenga/zotero-mcp:main. It is also possible to use the docker-based installation to talk to the local Zotero API, but you'll need to modify the above command to ensure that there is network connectivity to the Zotero application's local API interface.
Information on making changes and contributing to the project.
Clone this repository
Install dependencies with uv by running: uv sync
Create a .env file in the project root with the environment variables above
Start the MCP Inspector for local development:
npx @modelcontextprotocol/inspector uv run zotero-mcpTo test the local repository against Claude Desktop, run echo $PWD/.venv/bin/zotero-mcp in your shell within this directory, then set the following within your Claude Desktop configuration
{
"mcpServers": {
"zotero": {
"command": "/path/to/zotero-mcp/.venv/bin/zotero-mcp"
"env": {
// Whatever configuration is desired.
}
}
}
}To run the test suite:
uv run pytestBump the version in pyproject.toml and server.json (two places: the
server version and the package version).
Publish to PyPI with make publish.
Publish updated metadata to the official MCP
registry with make publish-mcp, authenticating first with mcp-publisher login github if
needed.
Build the container image with this command:
docker build . -t zotero-mcp:localTo test the container with the MCP inspector, run the following command:
npx @modelcontextprotocol/inspector \
-e ZOTERO_API_KEY=$ZOTERO_API_KEY \
-e ZOTERO_LIBRARY_ID=$ZOTERO_LIBRARY_ID \
docker run --rm -i \
--env ZOTERO_API_KEY \
--env ZOTERO_LIBRARY_ID \
zotero-mcp:localhttps://modelcontextprotocol.io/tutorials/building-mcp-with-llms
https://modelcontextprotocol.io/llms-full.txt can be utilized by LLMs
Item metadata is rendered from whatever fields the API returns rather than from a fixed list. Fields it omits are skipped, and fields this server doesn't know about appear under an "Other Fields" heading, so a Zotero upgrade never silently drops metadata.
The two APIs differ in one way worth knowing: the local API's quick search indexes citation keys, while the Web API does not, so searching for one returns nothing over the Web API even though the field is present in the data.
Get the full text content of a Zotero item, given the item key of a parent item or specific attachment.
| Name | Required | Description | Default |
|---|---|---|---|
| item_key | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool 'Get[s] the full text content', implying a read-only operation, but doesn't disclose behavioral traits such as authentication needs, rate limits, error conditions, or what happens if the item key is invalid. For a tool with zero annotation coverage, this is a significant gap in transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded: a single, clear sentence that states the purpose and parameter context without any wasted words. Every part of the sentence earns its place by conveying essential information efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (1 parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose and parameter semantics but lacks details on behavioral aspects, output format, or error handling. Without annotations or an output schema, the description should do more to be complete, but it meets the bare minimum for a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter with 0% description coverage, so the description must compensate. It adds meaning by explaining that 'item_key' refers to 'a parent item or specific attachment', which clarifies the parameter's purpose beyond the schema's generic 'Item Key' title. However, it doesn't provide details on format, examples, or constraints, leaving some ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get the full text content of a Zotero item' with the specific verb 'Get' and resource 'full text content'. It distinguishes from sibling tools like 'zotero_item_metadata' (which likely returns metadata) and 'zotero_search_items' (which searches for items). However, it doesn't explicitly contrast with siblings, so it's not a perfect 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by specifying 'given the item key of a parent item or specific attachment', which provides some context on when to use it. However, it lacks explicit guidance on when to use this tool versus alternatives like 'zotero_item_metadata' for non-full-text data or 'zotero_search_items' for finding items first. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get metadata information about a specific Zotero item, given the item key.
| Name | Required | Description | Default |
|---|---|---|---|
| item_key | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states it's a read operation ('Get'), but doesn't mention whether it requires authentication, rate limits, error conditions (e.g., invalid item keys), or the format of returned metadata. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('Get metadata information') and includes the key constraint ('given the item key'). There is no wasted text, repetition, or unnecessary elaboration, making it highly concise and well-structured for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 parameter, no nested objects) but lack of annotations and output schema, the description is minimally complete. It covers the purpose and parameter semantics adequately but misses behavioral details like authentication needs or return format. Without an output schema, the description should ideally hint at what metadata is returned, which it doesn't, leaving room for improvement.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning by explaining that 'item_key' is used to identify 'a specific Zotero item', which clarifies the parameter's role beyond the schema's generic 'Item Key' title. With 0% schema description coverage and only one parameter, this compensates adequately by providing context, though it doesn't detail the key's format or source. Baseline is high due to low parameter count.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'metadata information about a specific Zotero item', making the purpose immediately understandable. It distinguishes from 'zotero_item_fulltext' (which likely retrieves full text content) and 'zotero_search_items' (which searches multiple items) by focusing on metadata retrieval for a single item. However, it doesn't explicitly mention what metadata fields are included, keeping it from a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by specifying 'given the item key', suggesting this tool is for when you have a specific item identifier. It doesn't provide explicit when-to-use guidance versus alternatives like 'zotero_search_items' (e.g., use this for known items, use search for unknown items) or mention prerequisites like authentication. The context is clear but lacks detailed exclusions or comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for items in your Zotero library, given a query string, query mode (titleCreatorYear or everything), and optional tag search (supports boolean searches). Returned results can be looked up with zotero_item_fulltext or zotero_item_metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| qmode | No | titleCreatorYear | |
| tag | No | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It describes the search functionality and mentions that results can be looked up with other tools, which adds useful context. However, it doesn't disclose important behavioral traits like whether this is a read-only operation, what permissions are needed, pagination behavior beyond the 'limit' parameter, or error conditions. The description adds some value but leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in two sentences: the first explains the core functionality with key parameters, the second provides important follow-up context about sibling tools. Every word earns its place with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 4 parameters, 0% schema coverage, no annotations, and no output schema, the description does a reasonable job explaining the search purpose and parameters. However, it lacks information about return format, error handling, authentication requirements, and doesn't fully document all parameters (missing 'limit'). Given the complexity and lack of structured documentation, this leaves significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate. It explains the purpose of 'query', 'qmode' (with specific mode examples), and 'tag' (including boolean search support). It doesn't mention the 'limit' parameter, but covers 3 of 4 parameters with meaningful context beyond their names. This significantly improves understanding compared to the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Search for items'), resource ('in your Zotero library'), and scope ('given a query string, query mode... and optional tag search'). It distinguishes from siblings by mentioning that results can be looked up with 'zotero_item_fulltext' or 'zotero_item_metadata', indicating this is a search tool while siblings provide detailed item data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (searching the library with query parameters) and implicitly distinguishes from siblings by noting that results can be looked up with those tools. However, it doesn't explicitly state when NOT to use this tool or provide alternative search methods within the same tool family.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: zotero_search_items finds items, zotero_item_metadata retrieves metadata for a specific item, and zotero_item_fulltext gets full text content. There is no overlap or ambiguity between these functions.
All tools follow a consistent 'zotero_item_*' pattern with snake_case, using descriptive suffixes (fulltext, metadata, search_items) that clearly indicate their specific actions. The naming is uniform and predictable.
With only 3 tools, the server feels thin for a Zotero library management domain. While the tools cover basic search and retrieval, typical library operations like creating, updating, or deleting items are missing, suggesting an incomplete surface.
The tool set is severely incomplete for Zotero library management. It only supports search and read operations (search, get metadata, get fulltext), with no ability to create, update, delete, or manage items, collections, or tags, which are core to the domain.
Remote MCP server for full read/write access to a Zotero library
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kujenga/zotero-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
