Install Jentic One Beta

Connect the Mendeley API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Mendeley API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fapi.mendeley.com%2Fmendeley" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fapi.mendeley.com%2Fmendeley" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Mendeley API.

List and create documents in a researcher's Mendeley library with full bibliographic metadata

Update document fields and move documents to trash without permanently deleting them

Upload PDF files and download or delete files attached to library documents

Create, update, and delete annotations (highlights, sticky notes, and comments) on PDFs

GET STARTED

Start building with Mendeley API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Mendeley API for, with concrete tasks.

★ Citation Manager Sync

Build a sync layer between Mendeley and another reference manager or note-taking app by listing documents via /documents, fetching files via /files, and exposing annotations via /annotations. Researchers maintain Mendeley as the canonical library while reading and annotating in their tool of choice. Most teams ship a one-way sync in 3 to 5 days.

List all documents from /documents with a since filter for the last sync timestamp, fetch each file via /files/{id}, and copy any new annotations from /annotations into the secondary tool.

PDF Ingestion Pipeline

Drop a PDF into a watch folder and have an agent create a Mendeley document via POST /documents, then upload the file via POST /files. The agent extracts bibliographic metadata first by searching the catalog with /search/catalog or /metadata to deduplicate against existing entries. Typical setup is a day for the metadata-match flow.

Call /metadata with the PDF's extracted title and DOI, create a document via POST /documents using the matched catalog entry, then POST the file to /files with documentId set.

Annotation Export for Note Apps

Pull all highlights and sticky notes from a Mendeley library via /annotations and write them to a note-taking app such as Obsidian or Notion. Researchers use this to keep their reading notes searchable outside Mendeley. Typical effort is 2 to 3 days including incremental sync.

List annotations via GET /annotations, group them by document_id, and append each annotation as a markdown bullet under the matching paper's note in Obsidian.

AI Research Assistant

An AI agent assigned to a researcher can search the Mendeley catalog, add candidate papers to the user's library, and pull annotation history to summarise reading progress. Through Jentic, the agent calls Mendeley with OAuth-scoped credentials isolated from its prompt context. Setup is under an hour.

Use Jentic to search for 'search the Mendeley catalog', execute /search/catalog with the user's query, then add the top 3 results to the user's library via POST /documents.

Key Endpoints

27 endpoints — jentic publishes the only available openapi specification for mendeley api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/documents

List documents in user library

POST

/documents

Create a new document

POST

/files

Upload a PDF file

GET

/annotations

List annotations

POST

/annotations

Create an annotation

GET

/search/catalog

Search the Mendeley catalog

GET

/metadata

Find best matching catalog entry by metadata

POST

/folders/{id}/documents

Add a document to a folder

GET

/documents

List documents in user library

POST

/documents

Create a new document

POST

/files

Upload a PDF file

GET

/annotations

List annotations

POST

/annotations

Create an annotation

GET

/search/catalog

Search the Mendeley catalog

GET

/metadata

Find best matching catalog entry by metadata

POST

/folders/{id}/documents

Add a document to a folder

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the Mendeley API by hand means running its OAuth2 flow and coding your own calls to the documents, files, and annotations endpoints. Through Jentic you install once, import the Mendeley API from the API Directory, store the token once, and your agent calls it.

Permission scoping

Mendeley puts the folder id in the URL path (/folders/{id}/documents), while document and annotation targets travel in the request body, so limit the agent to the operations it needs, such as reading documents and searching the catalog, and leave adding documents to a folder out of the allowed set. Every operation you grant is your explicit choice.

Credential isolation

Your Mendeley token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'search my reference library' or 'add an annotation to a document', and Jentic returns the matching Mendeley operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Mendeley API through Jentic.

Why is there no official OpenAPI spec for Mendeley API?

Mendeley does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Mendeley API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

What authentication does the Mendeley API use?

Mendeley uses OAuth 2.0. Register an application in the Mendeley developer portal to obtain a client ID and secret, then run the OAuth flow to obtain an access token. Through Jentic, the OAuth tokens are stored encrypted in your Jentic One instance - agents receive only a scoped session at execution time.

Can I upload PDFs to Mendeley with the Mendeley API?

Yes. POST /files with the PDF as the request body and the documentId attached as a Link header. The file becomes the primary attachment for that library document and is available for download via GET /files/{id}.

What are the rate limits for the Mendeley API?

Mendeley does not publish per-second rate limits in the developer documentation; quotas are enforced at the application level by Elsevier. If you hit a 429, back off and contact Mendeley developer support to confirm the limit on your client ID.

How do I search the Mendeley catalog through Jentic?

Run pip install jentic, then search for 'search the Mendeley catalog'. Jentic returns the GET /search/catalog operation schema. Execute it with the query string and Mendeley returns matching catalog entries that you can then add to a user library via POST /documents.

Does the Mendeley API expose annotations made in the desktop and web apps?

Yes. GET /annotations returns highlights, sticky notes, and comments created across the Mendeley desktop and web clients. The annotations are linked to the underlying document_id so they can be aligned back to the paper PDF.

Can I limit what my agent is allowed to do with the Mendeley API?

Yes. Because Jentic One is self-hosted, you decide which Mendeley operations the agent may call, and it never touches anything you leave out of that allowed set. You might grant read-only access such as listing documents via GET /documents and searching the catalog via GET /search/catalog, while excluding writes like POST /folders/{id}/documents that add a document to a folder or POST /files that uploads a PDF. Every operation the agent can reach is your explicit choice, enforced by the rules in your own instance.

Mendeley API

Name: Mendeley API
Brand: Mendeley API
Availability: InStock

Agent-ready OpenAPI document · curated by JenticProductivityNote Takingoauth227 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Manage a Mendeley research library: list and create documents, upload and download PDF files, organise documents into folders, manage annotations, and search the Mendeley catalog by metadata.

Use for: List the documents in my Mendeley library updated in the last 7 days, Create a new Mendeley document for a paper titled 'Attention Is All You Need', Upload the PDF for document ID 'doc-9921' to Mendeley, Search the Mendeley catalog for 'graph neural networks for drug discovery'

Not supported: Does not handle full-text article licensing, peer review workflows, or journal submission - use for personal reference library and annotation management only.

Jentic publishes the only available OpenAPI specification for Mendeley API, keeping it validated and agent-ready. Mendeley is Elsevier's reference management platform used by researchers to organise papers, annotate PDFs, and collaborate via groups. The API exposes 27 endpoints covering documents, annotations, files, folders, the Mendeley catalog, academic disciplines, and metadata-based catalog search. It is suited to building citation managers, ingesting PDFs into research workflows, and synchronising library state between Mendeley and other research tools.

Jentic One on Github View OpenAPI Document

Connect the Mendeley API to your agent

Capabilities

Start building with Mendeley API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Mendeley API