"Tools and resources for PDF and XML document processing" matching MCP tools:

• swiftsign_send_envelope

  mcp

  Send a document for e-signature. Accepts PDF as base64, recipients, and field placement. Sandbox keys (sk_test_) send immediately (watermarked test mail). LIVE keys create a DRAFT and return it for human review unless confirm: true — nothing is emailed until confirmed. Field placement: page+x+y (percent, top-left origin) OR an anchor string, not both. After everyone signs, retrieve the sealed PDF with swiftsign_download_signed_pdf.

  Connector

• mindee_extract_document

  mindee

  Submit a document (PDF or image) to a Mindee extraction model and return the structured fields. Provide EITHER document_url (a public URL) OR file_base64 (+ filename). This enqueues an inference and polls until it completes (up to ~30s); if it is still processing it returns a job_id you can poll with mindee_get_job then read with mindee_get_inference. NOTE: consumes Mindee API credits (paid, billed per page). V2 API: POST /v2/inferences/enqueue.

  Connector

• create_letter

  PostAgent — Print and Mail

  Upload and normalize a FINISHED, ready-to-mail document to PDF. Choose this when the content is final and IDENTICAL for every recipient — including when you mail the same letter to many people (just quote/pay once per recipient with the same documentId). The exact bytes you give are what gets printed. Use create_template instead only when the content must vary per recipient via {{fields}}. Returns a documentId, the stored page count, byte size, and source format. Free; no payment required. Provide the document EXACTLY ONE way: `content` (inline text, for html/markdown/text), `contentBase64` (base64-encoded binary, for pdf/docx/image), or `url` (a publicly reachable URL the server fetches). Supplying none, or more than one, is an error. Maximum upload size is 31457280 bytes (~30 MB); output page size is US Letter. Any `{{...}}` text is printed LITERALLY here — it is NOT treated as a merge field. If you want personalized mail merge across recipients, use `create_template` instead. Reserved address zone: a recipient address block is printed over the top ~3 inches of page 1, so the server reserves that space for you automatically. For text/html/markdown/docx, page-1 content is pushed below the block (content may therefore flow onto an additional page); for pdf and image inputs, a blank first page is prepended. As a result the returned page count — and the selected-provider cost behind the resulting quote — can be higher than your source document (e.g. a single-page PDF is stored as 2 pages). You do NOT need to leave the top of your document blank yourself. See the postagent://formats resource for per-format details.

  Connector

• parse_pdf_to_text

  Nordic Financial MCP

  Download a PDF from a URL and extract all text content, page by page. Use this to read the full text of a specific document — for example, an annual report PDF linked from a search_filings result. Best combined with search_filings: use search_filings to locate the document, then parse_pdf_to_text for the full text. Do not use for PDFs that are already well-represented in the database — search_filings is faster and returns pre-ranked, relevant excerpts. Not suitable for scanned (image-only) PDFs without embedded text; those pages will be returned as "(no extractable text)". Args: pdf_url: Direct HTTPS URL to the PDF file, e.g. https://example.com/report.pdf. Must be publicly accessible; authentication-protected URLs will fail. Returns: All text from the PDF with "--- Page N ---" separators between pages. Returns an error string if the download fails, the URL does not point to a valid PDF, or the document exceeds the 60-second download timeout.

  Connector

• classify_document

  OpenWarrant — Document Verification Suite

  Classify a FINANCIAL document's type and issuing country. Specialised in financial-services documents: payslip, tax_invoice, bank_statement, salary_certificate, payg_summary, receipt. USE THIS WHEN someone shares a document (or a link to one) and asks: what kind of document is this? is this a payslip / invoice / bank statement? route this document. Also use it as the FIRST step before verify_document, so the right checks run. Provide the document ONE way: `url` (a public http(s) link to a PDF or image — fetched server-side, the cheapest call) OR `bytes_b64` (inline base64, plus `filename` for PDF-vs-image routing). Returns `{document_type, country_code, confidence, is_financial_document, evidence, ...}`. HONEST SCOPE: type classification only — NOT an authenticity or fraud judgment (use verify_document for that). Below the confidence threshold it abstains with 'unknown' rather than guessing; non-financial documents classify as 'other'. The document is never stored.

  Connector

• create_letter

  PostAgent

  Upload and normalize a FINISHED, ready-to-mail document to PDF. Choose this when the content is final and IDENTICAL for every recipient — including when you mail the same letter to many people (just quote/pay once per recipient with the same documentId). The exact bytes you give are what gets printed. Use create_template instead only when the content must vary per recipient via {{fields}}. Returns a documentId, the stored page count, byte size, and source format. Free; no payment required. Provide the document EXACTLY ONE way: `content` (inline text, for html/markdown/text), `contentBase64` (base64-encoded binary, for pdf/docx/image), or `url` (a publicly reachable URL the server fetches). Supplying none, or more than one, is an error. Maximum upload size is 31457280 bytes (~30 MB); output page size is US Letter. Any `{{...}}` text is printed LITERALLY here — it is NOT treated as a merge field. If you want personalized mail merge across recipients, use `create_template` instead. Reserved address zone: a recipient address block is printed over the top ~3 inches of page 1, so the server reserves that space for you automatically. For text/html/markdown/docx, page-1 content is pushed below the block (content may therefore flow onto an additional page); for pdf and image inputs, a blank first page is prepended. As a result the returned page count — and the selected-provider cost behind the resulting quote — can be higher than your source document (e.g. a single-page PDF is stored as 2 pages). You do NOT need to leave the top of your document blank yourself. See the postagent://formats resource for per-format details.

  Connector

• fluxink-mcp-chatgpt-create-layout

  fci-mcp

  FluxInk document layout generator. Transform raw text content into a structured PDF using one of seven study or work templates, then preview it in an embedded PDF viewer widget. Supported layout_type values. cornell is the Cornell note taking layout with cue, notes, and summary. bullet_points is a clean bulleted summary. zettelkasten is atomic linked notes. journalism_5w1h is who, what, when, where, why, and how. meeting_add is a meeting agenda plus action items. sq3r is Survey, Question, Read, Recite, Review study notes. pso is Problem, Solution, Outcome. Use this when the user asks for a Cornell sheet, bulleted summary, Zettelkasten card, 5W1H breakdown, meeting agenda or minutes, SQ3R study sheet, or PSO writeup. Use this when the user wants to turn raw notes, lecture transcript, or source material into a printable PDF or formatted study sheet. Use this when the user asks for a downloadable PDF document of their content. Do NOT use this when the user just asks for a plain summary in chat. Give it inline. Do NOT use this when the user wants to handwrite or draw something. Call show_handwriting_canvas instead. Do NOT use this when the user wants text in a personal handwriting style. Call show_style_canvas instead. Do NOT use this for plain informational requests with no document generation intent. Always pass the source material verbatim in the content parameter. Do NOT pre summarize. The layout engine handles structuring. Pick the layout_type that best matches the stated purpose. If unclear, ask one short clarifying question instead of guessing. Do NOT re-call if a layout PDF is already visible from a previous turn unless the user explicitly asks for a different layout, different content, or a regeneration. After calling, write a single short acknowledgement and do NOT restate the PDF content.

  Connector

• get_pdf

  turnale

  The printable PDF itself, returned as a base64 embedded resource — use this when the organiser wants the file handed to them and your client cannot fetch URLs. Default "sheet": the merged tournament document (match sheet with write-in score boxes, player sheet, standings/results when they exist). "results" and "plan" are deprecated pre-merge variants kept for comparison. For a lighter response, get_pdf_link returns download URLs instead.

  Connector

• get_recent_activity

  ExpenseBot

  Show what the user (or their AI assistants) has recently done in ExpenseBot via this MCP server: which tools were called, when, with what arguments, and whether they succeeded. This is a log of assistant TOOL CALLS, not the processing history of a document. Useful for questions like 'what did I do this week' or 'which tools has my assistant run', and to give the user transparency into AI-assisted actions. Returns the most recent N entries from the audit log (default 20, max 100).

  Connector

• well_create_invoice_document

  Well

  Render an existing invoice as a print-ready PDF and attach it as the invoice's source document. The letterhead carries the issuing company's own mark when Well has one on file, and otherwise sets the issuer's name as text. Never promise a logo. Use this tool when the user asks to generate, render, or attach a PDF for an invoice that already exists in the workspace. This does NOT email or send the invoice anywhere — it only creates and attaches the file. REQUIRED: invoice_id (the invoice must already exist) Refused if the invoice is already linked to a REAL ingested document (an upload, a connector import, or a provider-issued PDF) — that source of truth is never overwritten. Returns { success: true, invoice_id, document_id, reference_number, file } on success, or { success: false, error } on failure. `file` carries the rendered PDF's name and size plus the links to fetch it: `download_url` (saves the file), `signed_url` (opens it), and `app_url` (the document in Well). Hand the user `download_url` when they ask for the PDF itself. Both signed links stop working at `expires_at`; `app_url` does not.

  Connector

• validate_invoice_xml

  Attestwire

  Validate an e-invoice FILE the user already has, in either EN 16931 syntax and of either document type. Reads a UBL 2.1 Invoice, a UBL 2.1 CreditNote or a UN/CEFACT CII CrossIndustryInvoice (which carries invoices and credit notes alike) into the invoice model and runs EN 16931 plus the CIUS rules (XRechnung UBL and CII, Peppol BIS 3) over it, returning the same teaching errors as validate_invoice, plus which syntax it read, the document's BT-24/BT-23 and a list of everything in the file that did not reach the model. Use it when someone says "this invoice was rejected, why?" and hands you a file. Send the file as-is; do not work out the syntax or the document type first, because the tool decides both from the root element and reports what it found in `syntax` and in the invoice model's BT-3. XML ONLY, NOT A PDF: Factur-X and ZUGFeRD are CII XML inside a PDF/A-3 container, and this tool cannot open the container — extract the XML and send that. A PDF is refused with an explanation; do not retry it. A credit note is NOT refused — send it exactly like an invoice. It is a pre-flight, not an authority: a file that passes here can still be rejected by KoSIT or by a receiving platform. REQUIRES AN API KEY and costs 1 document.

  Connector

• firecrawl_parse

  firecrawl-mcp

  Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call.

  Connector

• get_us_statute_section

  Vaquill

  Get metadata for a specific US statute or regulation section by act_id (e.g. 'USC_T42_C21_S1983'). The act_id comes from search_us_statutes results or ask_legal_question sources. Returns citation, title hierarchy, breadcrumb, and links to HTML, PDF, and XML formats. Use before get_us_statute_section_text to preview a section.

  Connector

• convert_document

  Carbone MCP

  Convert any document to another format without storing a template. Supports 100+ input/output format combinations: Office documents, PDFs, images, web pages, spreadsheets, and more. The source file can be a local path, a URL, or a base64 string. Carbone tags are PRESERVED, not resolved: converting a template keeps every {d.field} intact, so this is also how you proof a template in another format (DOCX template → PDF, or DOCX → ODT while it stays a template). Use render_document instead when you need data injection ({d.field} tags resolved), translations, or batch generation. Common conversions: DOCX → PDF (file: "report.docx", convertTo: "pdf"; add converter: "I" for the fastest DOCX→PDF path), XLSX → PDF (file: "data.xlsx", convertTo: "pdf"), PPTX → PDF (file: "slides.pptx", convertTo: "pdf", converter: "O" for best fidelity), HTML → PDF (file: "page.html", convertTo: "pdf", converter: "C" for full CSS/JS rendering), DOCX → HTML (file: "doc.docx", convertTo: "html"), XLSX → CSV (file: "sheet.xlsx", convertTo: "csv"), PDF → PNG (file: "doc.pdf", convertTo: "png"), PPTX → PNG (first slide as image), MD → PDF (file: "readme.md", convertTo: "pdf").

  Connector

• get_analysis_status

  hypathesis

  Check the processing status of an uploaded paper. Poll this tool after uploading a PDF until status is 'Ready' before calling get_variable_relationships. Args: file_id: The file_id returned by the /upload endpoint. authorization: Optional. API key as 'Bearer hk_...' or 'hk_...'. Returns: { "status": "Processing" | "Ready" | "Empty" | "Ineligible" | "Pending", "edges_count": int, "variables_count": int }

  Connector

• ris_get_document

  ris-austria-mcp-server

  Fetch one RIS document’s full text or its rendition URLs, with explicit binding status and the amtssigniert authentic PDF surfaced wherever it exists. Address the document exactly one of two ways: document_number plus application (both copied verbatim from a ris_search_* or ris_lookup_citation result), or a document_url from a result’s content_urls — or, for a draft’s companion documents (Erläuterungen, Textgegenüberstellung, WFA, cover letter, annexes), a ris_search_drafts record’s materials[].url, which is the only route to them. format: markdown (default — the HTML rendition converted to markdown), html (raw HTML rendition), xml (the RIS Nutzdaten XML), or urls_only (no fetch — every rendition URL, including the Authentisch PDF). Format availability varies by application and the tool degrades explicitly, never silently: consolidated law, gazettes, case law, drafts, and most sectoral collections carry full text; district and municipal promulgations and court rules (Bvb, GrA, KmGer) publish only the signed authentic PDF; party-transparency decisions and council minutes (Upts, Mrp) are PDF-only; the 1848–1940 imperial gazettes (BgblAlt) are metadata-only — for these a text-format request returns a format_unavailable notice with the usable URL, not an error. Every result carries binding_status; only authentic (amtssigniert) publications are legally binding. This tool returns content, not fresh metadata — the metadata rides the search/lookup step that produced the document number. When the markdown text overflows the 40,000-byte budget the tool returns an outline (kind: outline) instead of truncating: the document’s §/Artikel/Anlage sections where it carries at least two such headings, otherwise contiguous byte windows named Part 1 of N … Part N of N covering the whole text and listed in document order. Re-call with sections:[…] naming outline entries to retrieve just those; a name matching no entry returns the outline again with a notice rather than the whole document. Windows are cut at line breaks, not at sentence or § boundaries, so one can open mid-sentence — read them in order and pull the neighbour when a passage straddles a cut. Raw html and xml renditions are never sliced and return whole at any size. Markdown drops the screen-reader expansions RIS ships alongside each abbreviated citation, keeping the visible citation form; raw html/xml renditions are returned exactly as published.

  Connector

• create_letter

  PostAgent

  Upload and normalize a FINISHED, ready-to-mail document to PDF. Choose this when the content is final and IDENTICAL for every recipient — including when you mail the same letter to many people (just quote/pay once per recipient with the same documentId). The exact bytes you give are what gets printed. Use create_template instead only when the content must vary per recipient via {{fields}}. Returns a documentId, the stored page count, byte size, and source format. Free; no payment required. Provide the document EXACTLY ONE way: `content` (inline text, for html/markdown/text), `contentBase64` (base64-encoded binary, for pdf/docx/image), or `url` (a publicly reachable URL the server fetches). Supplying none, or more than one, is an error. Maximum upload size is 31457280 bytes (~30 MB); output page size is US Letter. Any `{{...}}` text is printed LITERALLY here — it is NOT treated as a merge field. If you want personalized mail merge across recipients, use `create_template` instead. Reserved address zone: a recipient address block is printed over the top ~3 inches of page 1, so the server reserves that space for you automatically. For text/html/markdown/docx, page-1 content is pushed below the block (content may therefore flow onto an additional page); for pdf and image inputs, a blank first page is prepended. As a result the returned page count — and the selected-provider cost behind the resulting quote — can be higher than your source document (e.g. a single-page PDF is stored as 2 pages). You do NOT need to leave the top of your document blank yourself. See the postagent://formats resource for per-format details.

  Connector

• convert_invoice

  invoicehub

  Convert an e-invoice between formats via the shared EN 16931 canonical model: parse the source document, re-serialize as the target, and validate the result before returning it — never a document that has not been checked. Format ids: "UBL_2.1" (OASIS UBL, the universal Peppol/EN16931 baseline), "UN_CEFACT_CII" (UN/CEFACT Cross Industry Invoice, required syntax for Chorus Pro/France and many ERP back-ends), "XRechnung_UBL" / "XRechnung_CII" (Germany's mandatory B2G format, XRechnung 3.0 — required for invoicing German public-sector buyers), "Factur-X" (France/Germany hybrid PDF+XML — a human-readable PDF/A-3 with the structured invoice embedded, common for French B2B). Binary formats (Factur-X) are base64 in both directions. Requires an API key on the Pro plan or above for any target beyond plain UBL_2.1 — call list_supported_formats to see current availability.

  Connector

• view_pdf

  KDAN PDF

  Display an already-uploaded PDF in an interactive viewer widget. Call this after delete_pdf_page, set_password, change_password, redact_pii, and redact_by_text_range to show the updated PDF. Also call when the user explicitly asks to (re-)display a specific PDF. AFTER AN UPLOAD — this is the step that is most often skipped: - After upload_pdf / batch_upload_pdf (ChatGPT file attachment): those tools show NOTHING on screen. If the user asked to see, open, view, read, or display the document, you MUST call view_pdf now — the upload alone does not display it. - After create_upload_page (widget upload): do NOT call view_pdf. That widget renders the PDF itself. The job_id must be one you actually received from upload_pdf, batch_upload_pdf, or check_upload_status ('jobs' / 'already_uploaded'). NEVER invent a job_id and never pass a filename as job_id. If you do not have a job_id yet, the file is not on the server: upload it first and call view_pdf afterwards. MANDATORY after this tool returns: 1. Render a markdown download link so the user can save the file: [Download {filename}]({download_url}) 2. Follow cta_instruction and append cta_text at the end of your reply.

  Connector

• cap_table_import_safe

  Lovie Company Formation

  Imports a SAFE from an uploaded SAFE PDF and stores the document in S3. USE THIS (not RecordCapTableInvestment) whenever the user provides or uploads a SAFE PDF file. Flow: (1) call GetOcrUploadUrl with kind=SAFE and mime_type=application/pdf to get a presigned PUT URL + source_s3_uri, (2) upload the PDF bytes to that PUT URL, (3) call ImportSAFE with that source_s3_uri. This runs OCR to extract the terms; pass valuation_cap / investment_amount / discount_rate only to CORRECT a value the user says the OCR misread, and leave them empty to keep what the document says. Call ExtractSafeTerms first and get the user's confirmation before importing. effective_date is required — never import a SAFE without a date. If the company named on the document differs from this company, say both names and get the user's confirmation before importing. It copies the PDF to the canonical cap-table SAFE location, links it to a SAFE agreement, resolves the investor by name (matching an existing stakeholder or creating a new one), and creates the security. The security is marked signed only if the document is actually signed; an unsigned SAFE PDF is still stored and left committed. Whenever the user has the PDF — including when they attached it to this conversation — upload it and pass source_s3_uri so the document itself is stored; a SAFE created from typed terms alone has nothing on record proving its date or signature, and the cap table flags it as missing its document. Use RecordCapTableInvestment only for a SAFE the user genuinely has no document for. The response carries the cap table before this call, what it added, and the cap table after — report an import in exactly that order (current table, new additions, final table) and take the totals from the response rather than reading the cap table again. For several SAFEs at once, list every one you are about to add and get a yes before the first call, not after the last.

  Connector