ChatGPT Plugin

Paperguide

Search and organize papers

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

Paperguide is an AI-native platform for scientific research and evidence synthesis. Search over 200 million academic papers, explore scientific literature, read full text from your saved research PDFs, and organize references in your Paperguide workspace. Discover research. Search papers and preprints from PubMed, arXiv, OpenAlex, and Semantic Scholar. Find relevant studies using natural language, refine results by publication year, citations, open-access availability, or PDF availability, and retrieve paper details by DOI or PubMed ID. Explore scientific findings, compare studies, and plan literature reviews with links to the sources. Read and organize papers. Save research papers by DOI or PDF link, retrieve available full text from saved references, and ask questions about their methods, results, and conclusions. Search within attached PDFs, create or rename folders, and organize your references across research projects. Support systematic reviews. Access your existing reviews, identify papers missing PDFs, attach available full-text documents, and track PDF processing to support screening and evidence extraction within Paperguide. Built for students, PhD researchers, academics, clinicians, and research teams conducting literature searches, evidence synthesis, and systematic reviews. A Paperguide account is required. Some research and full-text operations use Paperguide AI credits; full-text access depends on document availability and account permissions. Review screening and extraction take place in Paperguide.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: Account required
First tracked: 2026-10-22
Tool count: 23
Geography: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce Paperguide has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

23 tools agents can invoke

Add a paper to the user's Paperguide reference manager. Pass a DOI (metadata is looked up automatically), the url of a PDF file, or both (metadata from the DOI, PDF from the url). With only a url, also pass the title (and authors, year, journal) if you know them; without them the PDF is read to identify the paper, which may end with a request for the title. By default the PDF is fetched and attached in the background: the result carries an import job to follow with get_import_status. Duplicates are refused with the existing reference id. Free. PDFs are fetched by Paperguide's own import service; see https://helpcenter.paperguide.ai/mcp/reference-manager for the sources it uses and size limits.
add_reference
Add references in the user's Paperguide reference manager to a folder while keeping the folders they are already in (nothing is duplicated — the same reference is simply filed in one more folder). References filed this way leave the default "Unorganised" folder. To take references out of their other folders, use move_references. Free.
add_references_to_folder
Attach PDFs to papers that list_missing_pdfs returned, up to 20 per call. Each item names the paper (paper_id or doi) and the file (a public url of the PDF, or the slot_id of an upload). Every item is reported back as accepted or rejected with a reason. Accepted PDFs are read in the background and each paper is then screened automatically; this uses the review's Paperguide credits. Refused for papers that already have a PDF. PDFs given by url are fetched by Paperguide's own import service; see https://helpcenter.paperguide.ai/mcp/systematic-review for sources and size limits.
attach_review_pdfs
Fetch a PDF and attach it to a reference in the user's Paperguide reference manager, in the background. Pass the url of the PDF file; without a url an open-access PDF is looked up from the reference's DOI. Refused when the reference already has a PDF. Follow the returned job with get_import_status. Free. PDFs are fetched by Paperguide's own import service; see https://helpcenter.paperguide.ai/mcp/reference-manager for the sources it uses and size limits.
attach_pdf
Whether each paper in a review has a usable PDF: ready, processing or missing (with the reason). Pass paper_ids to follow an attach; without them, counts plus the papers that are not ready. "verified" says whether the file was confirmed to be that paper by the DOI printed in it. Poll after poll_after_seconds while any are processing. Free.
get_review_pdf_status
Status of a background import started by add_reference or attach_pdf. Poll after poll_after_seconds while terminal is false; next_action says what to do when the job needs input. Free.
get_import_status
Create a folder in the user's Paperguide reference manager, at the top level or inside an existing folder (parent_folder_id from list_folders). Folder names must be unique within the library, and in a shared library a sub-folder can only be created inside a folder the user created themselves. Then file references into it with move_references or add_references_to_folder. Free.
create_folder
Supply the title (and authors, year, journal, DOI if known) for an import job whose status is needs_metadata: the PDF was stored but the paper could not be identified from it. Creates the reference and attaches the stored PDF. Free.
complete_import
Current plan and AI-credit usage for the account this connection bills: credits used and remaining in the current billing cycle, the reset date, usage by feature, and what each paid tool costs. Call this before credit-heavy actions to warn the user if credits are low. When billed to an organization, the shared pool and plan are visible only to the organization's owners and admins; other members see their own usage. Free.
get_usage
A short-lived link to upload one PDF file you already have (for example a paper fetched through the user's own access) directly to Paperguide storage with an HTTP PUT. Then pass the slot_id to attach_review_pdfs. Use a public url with attach_review_pdfs instead when the PDF is freely downloadable. Free.
create_pdf_upload_slot
Fetch full details for a single academic paper. Accepts the paper id from a previous search result, a DOI (e.g. "10.3390/nu11040673" or "https://doi.org/10.3390/nu11040673"), or a PubMed ID (e.g. "30935407" or "pmid:30935407"). Returns the abstract, summary, bibliographic metadata, external ids (DOI, PubMed, arXiv, OpenAlex), and BibTeX.
fetch
Full details of one reference in the user's Paperguide reference manager by id (from search_reference_manager or list_references): bibliographic metadata, abstract, folders, tags, attachment status (has_pdf = full text searchable), and a BibTeX entry. Free.
get_reference
Papers in a systematic review whose full text is still missing, with DOI, title, year and first author to search for. With full-text screening on, only papers that passed title/abstract screening are listed; without it, the included papers data extraction will read. stage_note explains when other papers are not ready yet, so relay it to the user. Pages of 50. Free.
list_missing_pdfs
List the user's Paperguide reference-manager libraries available to this connection, with the number of references in each. Call this first when the user asks about their own saved references or papers and the connection is billed to an organization, then pass the chosen id as workspace_id to the other reference-manager tools. Free.
list_reference_managers
Folders in the user's Paperguide reference manager, as a flat list with each folder's path in the tree and how many references it holds directly. Use a folder id with list_references to browse one folder. The default folder ("Unorganised") holds references not filed anywhere else. Free.
list_folders
Page through the references in the user's Paperguide reference manager, newest first — the whole library, or one folder (folder_id from list_folders). Returns lean rows (title, authors, year, DOI, journal, has_pdf) with paging info; call get_reference for the abstract, folders, tags and BibTeX of any row. Free.
list_references
The user's systematic reviews in Paperguide, with the stages each one runs and whether the caller may attach PDFs. Start here before list_missing_pdfs or attach_review_pdfs. Free.
list_systematic_reviews
Removes the given references from every folder they are in and files them in exactly the given folders (cut and paste) in the user's Paperguide reference manager. A reference may be in several folders at once, so to file a reference somewhere while keeping its current folders use add_references_to_folder instead. Pass only the default "Unorganised" folder to un-file references. Free.
move_references
Read the extracted text of the PDF attached to a reference in the user's Paperguide reference manager, in numbered parts (a paper is too long for one result). Call with part 1, then keep calling with next_part while has_more is true. Text keeps headings and, where available, "[Page N]" markers for citing pages. Use this when the user wants a paper summarised, reviewed or turned into a report; for a specific question about the paper, search_reference_manager_full_text is cheaper and returns only the relevant passages. Costs 10 credits per part.
get_reference_full_text
Rename a folder in the user's Paperguide reference manager (folder_id from list_folders). The default "Unorganised" folder cannot be renamed. Free.
rename_folder
Search over 200M+ academic papers by topic or question. Returns matching papers with title, authors, journal, publication date, citation count, abstract, DOI, and a citation URL. Use the returned id with the fetch tool to get full details for one paper. For papers the user has saved in their own Paperguide library, use search_reference_manager instead.
search
Semantic search over the full text of the PDFs attached to the user's saved references in their Paperguide reference manager. Returns the most relevant passages with page number and the reference they come from (with BibTeX), for answering questions about what the user's own papers say. Search the whole library, or pass reference_ids (from search_reference_manager) to search specific papers. Only references with has_pdf = true are searchable.
search_reference_manager_full_text
Find references the user has saved in their Paperguide reference manager, by title words or by DOI. Use this when the user refers to papers in their own library ("my saved papers", "the paper I added about …"). Returns bibliographic details and BibTeX for each match, plus has_pdf indicating whether its full text can be searched with search_reference_manager_full_text. Does not search the public literature — use search for that. Free.
search_reference_manager

FAQs

Paperguide ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Paperguide's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.