Undermind

Undermind is your AI co-researcher for the scientific literature. Ask a research question and Undermind searches the literature for you. It follows citation trails, evaluates hundreds of papers, and comes back with a ranked reading list rather than a page of keyword matches. With Undermind you can: - Run deep literature searches. Undermind's search agents explore a research question for a few minutes, then report back with a summary and a ranked list of relevant papers. - Look up papers by topic, author, title, DOI, or citation relationships (papers citing or cited by a paper you know), with abstracts and citation metrics. - Ask questions about a paper's full text, including its figures, tables, and equations, and check the answers against the source. - Keep your work organized in workspaces with folders, starred papers, saved searches, and notes, all synced with your account at undermind.ai. Scientists at thousands of research institutions use Undermind, from university labs to pharma R&D teams. Use it to check whether an idea is new, get oriented in an unfamiliar field, or track down the one method paper you need. You'll need an Undermind account (free or paid) and to sign in when connecting.

View in the ChatGPT registry

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Data & Analytics
Primary Subcategory: Academic Literature Search & Research Assistants
Secondary Subcategories: None listed
Brand: Undermind
Access: Account required
First tracked: 2026-08-12
Tool count: 24
Geography: US

ChatGPT Plugin Discoverability Score

ChatGPT organic discovery is not live yet

Undermind is tracked in the ChatGPT Plugin registry. Public organic-discovery measurement is not live for ChatGPT yet, so there is no score to publish today.

Get notified when your score goes live

Enter your work email and we’ll notify you when ChatGPT Plugin organic discovery scoring launches.

No spam. Unsubscribe any time.

Talk to our team

Primary Subcategory

Competing in ChatGPT Academic Literature Search & Research Assistants

View Category

Listed in alphabetical order

Primary Subcategory

Agentic Search by LinerOrganic discovery is pendingGet the score at launch

alphaXivOrganic discovery is pendingGet the score at launch

Article GalaxyOrganic discovery is pendingGet the score at launch

NYCU LibraryOrganic discovery is pendingGet the score at launch

Precise Special FunctionsOrganic discovery is pendingGet the score at launch

UndermindOrganic discovery is pendingGet the score at launch

Score explained

How the Discoverability Score works

Organic discovery scoring for Undermind on ChatGPT is not live yet. The score will use measured agent conversations when it launches.

InvisibleBuriedEmergingCompetitiveWinning

Organic discovery scoring is pending. Your Plugin score will appear on this scale when measurement goes live.

FoundDiagnostic

Whether Claude found your Plugin in connector search. It must be Found before it can reach the picker, but the score counts picker appearances—not search results.

PickedMain score

How often your Plugin appeared in the picker, or Claude invoked it directly, across contested conversations. This percentage is the Discoverability Score; the headline number is rounded.

PositionedDiagnostic

What position your Plugin appeared in when it was shown in the picker. This shows prominence, but it does not affect the score.

Read the full scoring methodology Recommended guideHow to get your Claude Connector organically discoveredFollow the practical steps agents use to find, shortlist, and choose your Connector.

Tools

24 tools agents can invoke

Add papers to a folder.
add_papers_to_folder
Create a new folder.
create_folder
Creates a new workspace and returns its title and workspace_id. Use the returned workspace_id with workspace-scoped tools. Requires a non-empty 'title'.
create_workspace
Delete a deep search.
delete_deep_search
Delete a file
delete_file
Delete a folder. Folder must be empty.
delete_folder
Find or disambiguate academic papers by author. Returns cite keys grouped by likely author identity and confidence.
find_papers_by_author
Undermind helps you find, read, and organize scholarly papers. Its tools work with both the global scholarly literature and workspaces containing papers, PDFs, deep searches, Markdown files, and folders. If you have not called this tool in the current conversation, call it before using the other Undermind tools. It explains what the tools do, how they work together, what workspaces and cite keys are, and how to refer to papers, files, folders, and deep searches. The response also tells you which Undermind account is connected.
get_orientation
Look up detailed metadata for papers, and where they are located in the workspace.
get_paper_info
Browse deep literature searches. Searches live in the workspace folder tree. Listings show each search's folder path; address a search by bare name (when unique) or by full path (e.g. '/analysis/my-search') when the name repeats across folders. - names=[] → All searches (folder path, status, timestamps) - names=['initial-search'] or ['/analysis/initial-search'] → Search details (goal, summary of results, timestamps, relevant papers) - names=['initial-search'], status_only=True → Just path + status and timestamps (fast, for polling) - names=['initial-search'], papers_only=True → Relevant papers list + search status, without goal or summary; use this for repeat/paginated reads
inspect_deep_searches
Browse files and folders. - paths=[] → Shallow listing of root - paths=['/analysis/'] → Shallow listing of folder - paths=['/analysis/my-research'] → Full file content
inspect_files
Browse the workspace's folders and their papers. - folders=[] → the folder tree: each folder with its direct file, search, and paper counts - folders=['/literature/crispr-delivery/'] or ['crispr-delivery'] → that folder's direct contents: subfolders, files, searches, and papers
inspect_folders
Launch a comprehensive review of the scholarly literature that runs asynchronously for several minutes. The tool returns immediately; use inspect_deep_searches with status_only=True for quick status checks. Ultimately produces a ranked list of papers and a summary, stored in the workspace. Only a few searches can run in parallel at once.
launch_deep_search
Lists workspaces available to the connected account, ordered by most recent activity.
list_workspaces
Look up specific papers from bibliographic information and return papers with cite keys. Use this to look up cite keys for particular papers by title, DOI, or citation entry. Accepts at most 300 items.
lookup_papers_by_metadata
Move deep searches to a different folder.
move_deep_searches
Move files to a different folder.
move_files
Move and/or rename a folder.
move_folder
Send sub-agents to read full-text PDFs and answer questions, summarize, or retrieve information. Each paper gets its own sub-agent that can see the entire PDF, including figures, tables, and equations. Multiple papers are read in parallel.
read_pdfs
Remove papers from a folder.
remove_papers_from_folder
Search for papers by semantic similarity. search_type chooses the source: global corpus, the 'library' pool of papers previously surfaced in the workspace, papers citing seed_papers, or papers referenced by seed_papers. sample_abstract is always used as the semantic query within that source. Without sort_override, results are ordered by semantic similarity. With sort_override, the tool first keeps a bounded set of semantically similar candidates, then orders that set by date/year or citations per year before pagination; it is not a metadata sort over the whole source.
search_papers
Star papers.
star_papers
Unstar papers.
unstar_papers
Create or update a file. - To update content: provide content (full replace) or content_edits (targeted)
write_file

Undermind FAQ

How do I improve a ChatGPT Plugin's 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.

What are Undermind alternatives on ChatGPT?

As of 2026-08-14, Undermind competes with Agentic Search by Liner, alphaXiv, Article Galaxy, NYCU Library, Precise Special Functions, Scholar Gateway, SciSpace, Scite, Sider Scholar, Tailo Lens in ChatGPT Academic Literature Search & Research Assistants, ranked by public Discoverability Score.

Where is this profile measured?

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