check_availability
ChatGPTCheck article availability, access options, and pricing for scientific articles. Returns the available access options for each DOI: - Open Access: freely available, with URL. No purchase needed. - PDF Library: already in the user's archive; includes pdfDownloadUrl when present. - Subscription: available through an institutional subscription. - Token Access: available using prepaid tokens. - GenAI Rights: licensing for AI/LLM use, with price; this is the access option relevant to AI use cases. - Document Delivery: a purchase or rental option for the full document, with price. The response also includes a nextSteps field describing the access summary and the confirmation flow. Pairs with place_order, which is rejected unless the order is confirmed.
check_order
ChatGPTCheck the status of article orders placed with place_order, and get PDF download links when complete. Returns the order status, article metadata, and download links when ready. Order statuses: - Sourcing: the order is still being processed (see subStatus for details). Orders typically remain in this state for a period after placement before completing. - Completed / Delivered / Order Complete: the article is ready; downloadUrls contains the PDF link. - Failed: the order could not be fulfilled. downloadUrls fields, in priority order: 1. pdfUrl: direct PDF download (time-limited pre-signed S3 URL). 2. supplementalUrl: supplemental materials accompanying the PDF (archive containing PDFs, video, or audio). 3. rentalViewerUrl: rental viewer link (not a PDF), available when pdfUrl is not; supports an upgrade to a full PDF purchase. 4. accessUrl: external link to the publisher or unpaywall, from the initial check_availability result, available when none of the above are.
check_reuse_rights
ChatGPTCheck what reuse rights exist for a scientific article. Returns, for each intended use type (personal research, presentation, course pack, etc.): - a reuse right value: one of Unknown, ExplicitlyGranted, ExplicitlyDenied, RequestAQuote - whether the article can be ordered for that intended use Complements check_availability: check_availability reports access and pricing options, while check_reuse_rights reports the permitted uses of the content.
citation_graph
ChatGPTTraverse the scite citation graph from seed DOIs to discover connected papers by citation topology rather than keyword. Each edge is a citation: s (citing paper) -> t (cited paper). Use it to find prior art / foundations (direction="out"), impact and follow-on work (direction="in"), or both. Get seed DOIs from search_literature first, then traverse; feed interesting nodes back into search_literature or read_fulltext for content. This tool returns structure (edges + titles), not abstracts or full text. Seeds are automatically expanded to their linked preprint/published versions (e.g. an arXiv DOI and its journal DOI), so a paper split across two DOIs is traversed as one work with a merged citation pool; the extra DOIs appear in seeds and seed_coverage. Response: edges is a deduped list of {"s","t","d"} (d = hop distance from a seed); papers maps every DOI in the graph to its {title, year}. truncated is true when the max_edges cap was hit. Coverage — check before trusting the topology. seed_coverage maps each seed to how many of its edges resolved directly (hop 1); low_coverage_seeds lists seeds with too few to be reliable. Coverage is per-paper: it only follows references/citers scite resolved to DOIs, and arXiv-heavy (e.g. ML) papers often under-resolve, so a thin graph means missing edges, not a poorly-connected paper. For any seed in low_coverage_seeds, treat its topology as incomplete and fall back to search_literature for that paper. Citation intent (scite's differentiator). Set include_intent=true to annotate each edge with the smart-citation type (supporting / contrasting / mentioning) and the section it appears in — this turns the structure into an intent graph: you can see agreement vs. dissent, and method vs. background citations. Set include_snippets=true to additionally attach up to 3 snippets of the actual citing text (implies intent). Snippet text is returned only for open-access / unrestricted sources; closed-publisher citations still carry type and section. Custom "why was it cited?" classifications from `snippets`. scite's type is a fixed 3-way label (supporting / contrasting / mentioning). When you need a finer or domain-specific taxonomy — e.g. uses as baseline, extends the method, reuses the dataset, critiques an assumption, motivates the problem — read the snippets (the verbatim sentence the citing paper used) and classify each edge yourself into whatever scheme the task calls for. The snippet is the ground truth; treat scite's type/section as a prior, not the final answer. Group edges by your derived label to answer "why does this literature cite X?". When a snippet is too short to judge the intent, chain read_fulltext on the citing paper (edge s) to read the surrounding paragraph / section and recover the full rationale — snippets are ~1 sentence each, read_fulltext gives you the argument around them. Typical flow: citation_graph (structure + snippets) -> pick the edges that matter -> read_fulltext(dois=[citing paper]) with a targeted term to confirm why it was cited before you label it. Recording a screen. When you use this tool to screen literature — keeping some papers and dropping others with a reason — record those keep/drop decisions with report_citations (cited / excluded + reason_code), and citation_report will summarize the include/exclude funnel as a PRISMA-style audit. Deriving analyses from `edges` (no extra calls). The edge list is all you need for the classic citation-analysis questions — compute them directly: - Common references (shared foundations): traverse direction="out" from multiple seeds; take the DOIs that appear as t for every seed. - Common citers (who cites all of them, e.g. surveys/syntheses): direction="in"; DOIs appearing as s for every seed. - Bibliographic coupling (papers similar to a seed): direction="out" at depth 2; rank other papers by how many t references they share with the seed. - Co-citation (papers cited alongside a seed): `direction…
get_mcp_usage
ChatGPTReport the user's current Article Galaxy MCP quota. Returns: - status: AG plan tier (active, trial, freemium, disabled, or not_connected) - limit: monthly cap on AG tool calls (0 when not enabled) - used: AG tool calls consumed this month - remaining: calls still available this month - upgrade_url: link to upgrade the AG plan Usage counters reset monthly on the UTC calendar month boundary. This tool is read-only and does not consume quota.
get_order_history
ChatGPTList the user's Article Galaxy order history, newest first by default. Use this when the user asks what they have ordered. Examples: - "Get my latest 10 orders" -> limit=10 (the default) - "Get my latest 50 orders" -> limit=50 - "Get my oldest orders" / "sort ascending" -> sort_order="asc" - "Get my August orders" -> month="YYYY-MM" for August; with no year given, use the most recent August that has already started - "Get my orders for DOI 10.1038/nature12373" -> doi="10.1038/nature12373" Filters combine, e.g. month plus status="completed". Results: - table: a ready-made markdown table with columns Order Date, Order ID, DOI, Article, Status (Date), PDF. Show it to the user as-is. The Order Date header carries ↓ (newest first) or ↑ (oldest first). The PDF column holds a link icon to the delivered PDF on Article Galaxy, only for orders with a PDF available. - orders: the same rows as data (orderDate, orderId, doi, article, status, statusTime, pdfUrl). - totalRecords: how many orders match in total, when AG reports it. When the user refers to an order from the list, call check_order with its orderId for live status, reuse rights, or a direct (presigned) download link.
pdf_fetch
ChatGPTRead the extracted text of an Article Galaxy PDF by order_id, server-side. When to use: the default way to read a delivered PDF is to fetch its pdfUrl (from check_order / place_order) directly, which gives you the whole document including figures. Use pdf_fetch instead when your client cannot fetch URLs, when the paper is too long to load whole and you need to search or page within it, or for repeat reads (content is cached per order). Applies to completed orders that have a downloadUrls.pdfUrl, as reported by check_order. Availability: any login connected to an Article Galaxy platform (company) account. B2C card accounts get a pdf_fetch_unavailable result pointing at a platform account; pass that message on and offer the pdfUrl instead. Arguments: - order_id (required): the AG order ID returned by check_order. - query (optional): case-insensitive substring; returns matching context windows. Targeted queries (terms, section names, author names) return more focused results than broad ones. - page (optional): 1-indexed page number. Ignored when query is set. Defaults to page 1. - max_tokens (optional): approximate upper bound on returned text length. Default 2000. Returns JSON with: - total_pages: number of pages in the PDF. - when query is given: matches (a list of {page, context} entries), total_matches, truncated. - when page is given (or default): page, content, truncated. Notes: - Content is cached per order_id; repeat calls on the same order are fast. - A targeted query returns a focused context window; paging returns one page at a time. - Image-only or scanned PDFs return a pdf_appears_scanned error (OCR not yet supported). - Only AG order IDs are supported in this version; arbitrary URLs and link-resolver redirects are not supported yet.
search_literature
ChatGPTSearch scientific literature and read full-text content from peer-reviewed papers. Use dois (preferred) or titles with targeted term queries to extract full-text passages from specific papers. Each call returns up to 5 relevant excerpts (~500 chars each) — vary search terms across calls to read through a paper section by section. IMPORTANT — keep `limit` small. Use limit: 10-50 with offset for pagination. Large limits with full citations and excerpts produce very large payloads that consume significant LLM context. Calling with no parameters browses the corpus (210M+ papers, relevance-sorted). This is allowed for broad exploration but rarely what you want — pass term, dois, titles, or other filters for targeted results. What This Tool Returns: - Paper metadata: title, authors (first 3), abstract, DOI, journal, year, volume, issue, page - fulltextExcerpts: up to 5 passages (~500 chars) from the paper matching your query (OA only) - access: resolved access link with source, type (open/institutional/purchase), content type, and pricing - citations: Smart Citation statements — actual quoted text from citing papers, classified as supporting/contrasting/mentioning/unclassified (unclassified = statement present but classifier hasn't assigned a type) - tally: citation metrics (total, supporting, contrasting, mentioning, citing publications) - editorialNotices: editorial notices (retraction, correction, concern, erratum), each with status, noticeDoi, date - isOa, oaStatus, license: open access information Fetching Paper Metadata (no search term needed): Pass dois or titles WITHOUT a term to retrieve metadata for specific papers. Example: dois: ["10.1038/s41586-020-2012-7"] Full-Text Excerpts: For OA papers, fulltextExcerpts contains passages matching your query. If empty, the full text is not indexed or terms didn't match — use the access field for the best link to the PDF or full text. Smart Citations ARE Full-Text Evidence: - snippet: exact sentence/paragraph from the citing paper's full text - type: classification (supporting, contrasting, mentioning, unclassified) - section: paper section (Introduction, Methods, Results, Discussion) - sourceDoi: paper containing this snippet; targetDoi: paper being cited Search Capabilities: - Boolean operators: AND, OR, NOT - Phrase search: "exact phrase" - Proximity: "term1 term2"~5 - Field filters: title, abstract, author, journal, year, affiliation - Citation filters: supporting_from/to, contrasting_from/to, mentioning_from/to - Editorial filters: has_retraction, has_concern, has_correction, has_erratum Parameters: - term: cross-field search query (optional when dois/titles provided) - dois: array of DOIs to filter to specific papers - titles: array of titles to filter (use when DOIs unavailable) - limit: max results (default: 10, max: 1000) - offset: pagination offset - Plus 20+ filter parameters (see schema) Response Format: ``json { "hits": [{ "doi": "10.1234/example", "title": "Paper Title", "authors": [{"authorName": "Jane Smith"}], "abstract": "Full abstract text...", "year": 2023, "journal": "Nature", "tally": {"supporting": 32, "contrasting": 8, "mentioning": 5}, "fulltextExcerpts": ["Relevant passage..."], "access": {"url": "https://...", "accessType": "open", "contentType": "pdf"}, "citations": [{"snippet": "These findings...", "type": "supporting", "section": "Results"}], "editorialNotices": [{"status": "retracted", "noticeDoi": "10.1234/notice", "date": "2021"}] }] } ``
