Mendeley

Provides local access to Mendeley data via MCP, enabling library search, metadata retrieval, catalog queries, DOIs, and document creation.

python

0

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "pallaprolus-mendeley-mcp": {
      "command": "mendeley-mcp",
      "args": [],
      "env": {
        "MENDELEY_CLIENT_ID": "YOUR_CLIENT_ID",
        "MENDELEY_CLIENT_SECRET": "YOUR_CLIENT_SECRET",
        "MENDELEY_REFRESH_TOKEN": "YOUR_REFRESH_TOKEN"
      }
    }
  }
}

You can connect your Mendeley library to local or MCP-compatible clients using the Mendeley MCP Server. It acts as a bridge between your Mendeley data and conversational or automation tools, letting you search, retrieve, and add documents from your library and from Mendeley’s global catalog through simple MCP commands.

How to use

Use an MCP client to interact with your Mendeley MCP Server. You can search your library by title, author, abstract, or notes, browse folders, fetch full metadata, look up papers by DOI, and add new documents to your library. The server runs locally on your machine, and credentials are stored securely on your system.

To get started, ensure your MCP client is configured to connect to your local server. When you issue a command through the client, the server will forward requests to the Mendeley API and return results you can present to the user or include in your workflow.

Common workflows include:

Searching for papers by topic and retrieving abstracts
Listing documents within a specific folder or collection
Looking up papers by DOI and summarizing them
Adding a new document to your library with title, authors, and metadata

How to install

Prerequisites you need before installing the Mendeley MCP Server:

A Mendeley account (Elsevier authentication)
A registered Mendeley API app with Client ID and Client Secret
A supported runtime environment for your platform (Python, uv, Docker)

Install the MCP server using any of the following methods.

pip install mendeley-mcp

uv tool install mendeley-mcp

docker run -it \
  -e MENDELEY_CLIENT_ID="your-client-id" \
  -e MENDELEY_CLIENT_SECRET="your-client-secret" \
  -e MENDELEY_REFRESH_TOKEN="your-refresh-token" \
  ghcr.io/pallaprolus/mendeley-mcp

If you prefer building locally from source, clone and install in editable mode.

git clone https://github.com/pallaprolus/mendeley-mcp.git
cd mendeley-mcp
pip install -e .

From source install flow (alternative steps)

For development or custom runs you can install from source and run the server directly.

git clone https://github.com/pallaprolus/mendeley-mcp.git
cd mendeley-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

Available tools

mendeley_search_library

Search documents in your library by title, author, abstract, or notes.

mendeley_get_document

Retrieve full details of a specific document, including metadata and abstracts.

mendeley_list_documents

List documents with optional filtering by folder or collection.

mendeley_list_folders

List all folders or collections within your Mendeley library.

mendeley_search_catalog

Search Mendeley’s global paper catalog for papers and metadata.

mendeley_get_by_doi

Look up a paper by its DOI to fetch bibliographic details.

mendeley_add_document

Add a new document entry to your Mendeley library.