MCP App Store
by KeenEthics

Overview

CiteLLM is the verification layer for answers from your documents. Ask ChatGPT about a PDF, such as figures from a 10-K, a clause in a contract or the key points of a report, and every answer comes with a precise citation: the page and passage it came from, highlighted in an interactive viewer. Click any answer to jump to its source and verify it in seconds. Calculated figures show their formula with each input highlighted. Review up to 20 PDFs and 100 answers at once, and export a highlighted PDF or an evidence report. Try it without an account, or sign in with Google for higher limits; your PDFs are private and temporary by default.

Tools

citellm_delete_pdf

ChatGPT
Deletes a PDF from CiteLLM with its saved reviews and viewer access. Use when the user asks to remove a PDF from CiteLLM. Does not delete the original attachment, the conversation, downloaded copies or backups.

citellm_export_pdf

ChatGPT
Create a highlighted PDF. Set highlighted_pages_only to export only pages containing matched highlights, once each in original document order.

citellm_export_report

ChatGPT
Create an evidence report PDF for an audit or compliance file from a saved review: cover with source hash and sign-off, claim summary, each claim with its located passages and cropped highlights, highlighted source pages, reviewer decisions and method.

citellm_export_xlsx

ChatGPT
Create an Excel workbook from a saved review: one row per claim with its status, PDF pages, quotations, calculation, assessment, follow-up question and reviewer decision, the follow-up questions on their own sheet, decisions and method. A tie-out lists each draft item with its sources. A comparison exports as its matrix of values instead.

citellm_list_templates

ChatGPT
Returns the comparison templates available to this account: built-in field lists for leases, NDAs, insurance quotes, SOC 2 reports, credit agreements and research studies, and templates the account saved. Each has an id, name, description and fields with ids and labels.

citellm_open_pdf_upload

ChatGPT
Opens CiteLLM's embedded file picker, where the user selects one or more PDFs from their device, up to the review limit, and uploads them directly to CiteLLM. Use when the user asks for the picker or when the attachment cannot be transferred another way. Accepts an optional upload_id to reuse an upload ticket that was already prepared. Each uploaded PDF's session_id is available for page reading and reviews.

citellm_prepare_pdf_upload

ChatGPT
Creates an upload ticket for one user-selected PDF, or with file_names for several, that the host holds as local files in a code-execution sandbox; each file is one upload on the ticket. This call does not transfer or import the PDF: the returned HTTPS endpoint accepts the original PDF bytes by HTTP POST with the supplied headers, and a successful upload returns HTTP 200 with a session_id. The ticket expires after a few minutes and allows one upload attempt per file.

citellm_read_pdf

ChatGPT
Imports one user-selected PDF for questions about it and claim checking. Input: its host-provided HTTPS attachment URL; local paths, PDF bytes and base64 are not supported inputs. Extracts the text and returns a session_id, the page count, the text of the first pages and the expiry time (null when the PDF is saved until deleted). Returns source text, not verdicts.

citellm_read_pdf_pages

ChatGPT
Returns extracted source text for a requested page range of an existing PDF session, by session_id, start page and optional page count of up to 20. The result covers only the requested range, and stops early at the server's text budget; next_page is the first page not returned.

citellm_refresh_pdf_access

ChatGPT
Renew short-lived viewer access after checking document ownership.

citellm_review_evidence

ChatGPT
Displays answers and claim assessments about PDFs with highlighted source evidence in one interactive viewer, and saves a review identified by review_id. Takes the draft_id of a validation, or the complete claims. One request supports up to 100 claims per PDF and up to 20 PDFs (additional_documents) as document tabs. Each claim takes source quotations, optional page hints (page 1 is the first page of the file, including the cover) and, for a derived value, a calculation with the formula, substituted source values, units and result. Rejects the request without saving a review if a quotation does not match its PDF. insufficient_evidence marks a claim the source does not establish, and follow_up holds an optional question for whoever prepared the document, listed in the evidence report and the Excel export. Matching confirms where text appears, not whether a claim is true. tie_out ties a draft PDF to its sources, such as a covenant compliance certificate to the credit agreement and financial statements it reports on: session_id is the draft and tie_out.source_session_ids lists the source PDFs, in place of additional_documents. Each claim is then one figure or factual statement in the draft, in draft order, with draft_quote holding the exact draft text and source_session_id naming the source PDF its evidence quotes; a quotation from another source PDF names it in its own source_session_id, so one item can cite several sources, up to 12 quotations per item. A source_session_id may give only the first 8 characters of a session ID that the request gives in full. A session a quotation names that tie_out.source_session_ids leaves out is added as a source. A quotation may also come from the draft itself, under the draft's session_id, away from the text the item ticks: on another page, such as the draft's own schedule, or on the same page as an input to the item's calculation. supported marks a tied item (with calculation when derived), contradicted a draft value that differs from the source, partially_supported an item of which only some figures tie, and insufficient_evidence with no quotations an item no source states. A figure rounded from the source, such as $83.9 million from 83,872 in thousands, ties without a calculation. The viewer shows the draft with numbered tick marks beside the highlighted source passage and exports the ticked draft.

citellm_save_template

ChatGPT
Saves a named list of comparison fields to the signed-in CiteLLM account as a template, or deletes a saved template, by template_id. Saving an existing template_id replaces it. Each account keeps up to 50 templates of up to 30 fields.

citellm_search_pdf

ChatGPT
Searches the text of an imported PDF. queries returns the total matches, page and surrounding text for up to 25 case-insensitive phrases; definitions returns the full text of up to 10 defined terms ("Term" means ...), with the pages it spans and the other defined terms it uses; list_definitions returns every defined term with the page that defines it. Results locate text and are not evidence by themselves.

citellm_usage

ChatGPT
Show the current account tier, effective PDF limits and UTC daily/monthly usage. Paid status is checked by the server.

citellm_validate_evidence

ChatGPT
Checks quotation locations and numeric and calculation requirements for a complete set of claims across one or more imported PDFs, without opening a viewer or saving a review. A later call can give the draft_id of an earlier one with changes: the claims to replace, add or remove by claim number, all claims being checked again. Returns ready_to_display, a draft_id for exactly the claims checked, quotation-location failures in evidence_errors and numeric or calculation failures in validation_errors, retaining valid matches. Numeric claims pass only when their values appear in matched quotations or a calculation recomputes from quoted inputs. Matching confirms where text appears, not whether a claim is true. tie_out ties a draft PDF to its sources, such as a covenant compliance certificate to the credit agreement and financial statements it reports on: session_id is the draft and tie_out.source_session_ids lists the source PDFs, in place of additional_documents. Each claim is then one figure or factual statement in the draft, in draft order, with draft_quote holding the exact draft text and source_session_id naming the source PDF its evidence quotes; a quotation from another source PDF names it in its own source_session_id, so one item can cite several sources, up to 12 quotations per item. A source_session_id may give only the first 8 characters of a session ID that the request gives in full. A session a quotation names that tie_out.source_session_ids leaves out is added as a source. A quotation may also come from the draft itself, under the draft's session_id, away from the text the item ticks: on another page, such as the draft's own schedule, or on the same page as an input to the item's calculation. supported marks a tied item (with calculation when derived), contradicted a draft value that differs from the source, partially_supported an item of which only some figures tie, and insufficient_evidence with no quotations an item no source states. A figure rounded from the source, such as $83.9 million from 83,872 in thousands, ties without a calculation. The viewer shows the draft with numbered tick marks beside the highlighted source passage and exports the ticked draft.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Similar Apps