"Tools and methods for extracting text from PDF files" matching MCP tools:

• parse_pdf_to_textA

  Nordic Financial MCPA

  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.

  ConnectorNo auth

• scaffold_serviceA

  @imqueueA

  READ-ONLY: returns generated source code as text and writes nothing to disk, creates no project and runs no command. Generates an idiomatic @imqueue/rpc service (an IMQService subclass with @expose()d, JSDoc-typed methods) plus a bootstrap that starts it. Provide the methods you want, or omit them for a starter template. Any non-primitive parameter or return type also gets a types.ts with the required @classType()/@property() declarations — without those the generated client types it `any`, which compiles. Use create_service (local install only) if you want files actually written.

  ConnectorNo auth

• doc_extractA

  toolsA

  Converts a document to markdown or plain text: pass a public URL or the file itself as base64, and get back the content with headings, tables and lists preserved, at a fraction of the tokens that rendered pages cost. Use it when a harness has no native reader for the format — .docx, .xlsx, .odt and .numbers rarely have one — when a document is only a URL away, or when a long PDF's text matters and its layout does not. Handles PDF (.pdf), Word (.docx), Excel (.xlsx, .xlsm, .xlsb, .xls), OpenDocument (.odt, .ods), Apple Numbers, CSV, HTML, XML, and plain-text formats such as .txt and .md. The format is detected from magic bytes, not trusted from the file name, so a PDF served from a .php URL still converts. Two honest limits: a scanned PDF with no text layer has nothing to extract (this is conversion, not OCR), and legacy binary .doc and .ppt files are not readable — resave them as .docx or .pptx. Images are refused rather than described. Documents up to 10 MB.

  ConnectorNo auth

• parse_documentA

  Razi ToolsA

  Use this when the file ALREADY stores its text as characters: it decodes them and returns JSON { text, metadata } verbatim, with no guessing involved. That exactness is the whole difference from extract_text_ocr, which recovers text from pixels by guessing at glyph shapes and should only ever be pointed at a photo, screenshot or scan. Supported: .txt, decoded as UTF-8 and returned in full with metadata { format: "txt", words }; and .pdf, where the text layer is read page by page and joined with a `--- Page N ---` separator, returning metadata { format: "pdf", pages, words } — pages and words are counted from the document itself, never estimated. .docx and every other extension are rejected with 400. A scanned or photographed PDF has no text layer, so nothing can be extracted from it here; that case returns 422 with a metadata.imageOnly flag rather than an empty success, and extract_text_ocr is the tool for it. Limits: 50MB and 300 pages, over which the call returns 413; an unreadable or encrypted PDF returns 400. Layout is not preserved — no tables, columns or coordinates, just a flat string per page. The file type is decided by the filename extension, not by inspecting the bytes. 10 calls per minute per caller. There is no upload channel over MCP: pass `fileUrl`, a URL in razi.pro's own storage; third-party URLs are rejected. Obtain one by uploading the file over the REST API first (POST /api/v1/tools/execute with the file attached).

  ConnectorNo auth

• parse_documentA

  Razi Document ToolsA

  Use this when the file ALREADY stores its text as characters: it decodes them and returns JSON { text, metadata } verbatim, with no guessing involved. That exactness is the whole difference from extract_text_ocr, which recovers text from pixels by guessing at glyph shapes and should only ever be pointed at a photo, screenshot or scan. Supported: .txt, decoded as UTF-8 and returned in full with metadata { format: "txt", words }; and .pdf, where the text layer is read page by page and joined with a `--- Page N ---` separator, returning metadata { format: "pdf", pages, words } — pages and words are counted from the document itself, never estimated. .docx and every other extension are rejected with 400. A scanned or photographed PDF has no text layer, so nothing can be extracted from it here; that case returns 422 with a metadata.imageOnly flag rather than an empty success, and extract_text_ocr is the tool for it. Limits: 50MB and 300 pages, over which the call returns 413; an unreadable or encrypted PDF returns 400. Layout is not preserved — no tables, columns or coordinates, just a flat string per page. The file type is decided by the filename extension, not by inspecting the bytes. 10 calls per minute per caller. There is no upload channel over MCP: pass `fileUrl`, a URL in razi.pro's own storage; third-party URLs are rejected. Obtain one by uploading the file over the REST API first (POST /api/v1/tools/execute with the file attached).

  ConnectorNo auth

• attach_receiptA

  Caribooks (QuickBooks Online)B

  Render user-provided receipt text as a PDF transcription and attach it to a QuickBooks transaction. Intended for receipts that exist only as text, such as an email body or copied order confirmation. The PDF is visibly marked as a transcription, not an original document. Requires confirmed_by_user: true after the user explicitly requests a transcription, and full access on the connection. The receipt fields contain the original text and, when applicable, the actual email sender and subject. Does not transfer original uploaded files.

  ConnectorOAuth

• batch_upload_pdfA

  KDAN PDFA

  Upload multiple PDF files from ChatGPT file attachments. Use this when the user provides multiple file attachments in ChatGPT. Downloads each PDF from its signed URL and stores it. Returns session_id and a list of job_ids. Like upload_pdf, this ONLY works on hosts that resolve chat attachments for you (ChatGPT). On Claude and other MCP clients, call create_upload_page instead. Never invent or guess a download_url or file_id. MANDATORY WORKFLOW before calling this tool: 1. ALWAYS call check_upload_status FIRST — even if you think the files are new. 2. Only include files confirmed absent from check_upload_status. If ALL files are already uploaded, skip batch_upload_pdf entirely and reuse the existing job_ids. 3. Reuse job_ids from already_uploaded — do NOT re-upload those files. Skipping step 1 and calling batch_upload_pdf directly is FORBIDDEN. After batch_upload_pdf completes: if the user requested a comparison, call 'compare_pdfs' with the returned job_ids immediately.

  ConnectorNo auth

• merge_pdfsA

  PreteWorks APIA

  Combine 2+ PDFs into a single PDF, in the order given. Inputs are file_ids (from prior tools) or base64 PDFs. Returns a file_id (for chaining) and a ~1h download URL.

  ConnectorNo auth

• list_filesA

  TillpadA

  File catalog reads. view=files lists uploaded file metadata, optionally filtered by namespace, and checks ACL files_list. Returns {files}. view=supported_types returns kinds, extensions, mimeTypes, and extract notes for RAG uploads. That view checks no ACL and spends no quota (former files_types). Neither view writes, deletes, or sends email. Use index_document to upload. MCP indexing accepts UTF-8 text; REST multipart accepts PDF and Excel too.

  ConnectorAPI key

• t54_list_operationsA

  Agentic Swarm Marketplace (T54 x402 MCP)B

  Returns operationIds, HTTP methods, paths, and query parameter names from the bundled OpenAPI spec (no network). Use before t54_x402_request or per-SKU tools.

  ConnectorNo auth

• report_pdf_generateA

  AurelianFloA

  Return an inline PDF artifact from supplied report_meta, tables, metrics, and summary content; this read-only renderer does not persist hosted files. Use this only when a structured report payload already exists; use report_docx_generate for editable Word output or compliance_edd_report to build the memo first.

  ConnectorNo auth

• merge_pdfsA

  Sats4AI - Bitcoin-Powered AI ToolsA

  Merge multiple PDF files into a single document. Preserves bookmarks, links, and formatting. Returns JSON: { url } — a temporary download URL (valid ~1 hour). Minimum 2 files, no maximum. Files are concatenated in array order. 100 sats per merge regardless of file count. Use convert_file instead if you need format conversion (e.g., DOCX→PDF). Pay per request with Bitcoin Lightning — no API key, no account needed. Requires create_payment with toolName='merge_pdfs'.

  ConnectorNo auth

• create_media_postA

  WiplashA

  Upload ChatGPT files and publish one public image/PDF gallery, audio post, or video post as a selected agent owned by the signed-in human. Use list_my_agents first. Image/PDF galleries support up to eight files; audio and video posts require exactly one matching file. Temporary file URLs are accepted only through ChatGPT file handoff and are never returned or persisted by this connector. Call only after the user confirms the exact agent, category, files, title, body, tags, alt text, and optional karma reward.

  ConnectorNo auth

• list_payment_methodsA

  agentcardA

  List the saved payment methods (used only to pay for flight bookings, not for cards or adding funds). Returns each method with its id, brand, last 4 digits, and expiry, and marks the default one. Use setup_payment_method to add a new one. The gated tools set_default_payment_method and remove_payment_method also exist; call them by name even though they aren't in the tools list.

  ConnectorNo auth

• discoverA

  AgentMarketplaceA

  Discover AgentMarketplace's capabilities, tools, auth methods, and scopes. Call this first when connecting to AgentMarketplace to understand what's available and how to authenticate. No authentication required. Returns a catalog of available tools, resources, auth methods, and scopes.

  ConnectorNo auth

• extract.pdfA

  CallMeterA

  Extract page text and heuristic tables from a base64-encoded PDF for downstream reasoning. Call for general PDF text hops — receipt/invoice field extraction belongs to parse.receipt / parse.invoice. Inputs: file_base64 (or pdf/base64 aliases); optional options.includeTables / maxPages. Decoded size ≤ 10 MiB. Outputs pages[].text and optional tables. Paid (~10 credits / $0.10) via prepaid key or x402.

  ConnectorNo auth

• helvabase_upload_sourcesA

  Helvabase — Governed response dossiersB

  Transfer real selected source bytes after preview and user authorization. Supply only manifest-bound IDs and canonical base64 or UTF-8 text, up to 1 MiB combined (20 files). Never send paths, URLs, guessed content or authority overrides. For larger files use bearer-authenticated POST /mcp/files. Inspect each receipt: added/already_present are confirmed; pending keeps a reservation. Use helvabase_source_imports after interruption, then resumeImportId with the original bytes and a new recovery key. Skipped, pending, failed or conversion-required sources are not confirmed ingested. Business-library PDF, DOCX and XLSX require the backend binary capability and a complete extraction receipt; they remain unreviewed business evidence.

  ConnectorOAuth

• pdf_fillA

  PDFopsA

  Fill AcroForm form fields in a PDF and return the result. Field names must exist in the PDF (use pdf_inspect first). All values are strings; checkboxes take "true"/"false"; dropdown/radio/optionlist values must be one of the field's options; text values must respect the field's maxLength from pdf_inspect. The source PDF is never modified. Returns the filled PDF inline as an application/pdf resource. Encrypted PDFs are rejected with decrypt advice (common for government blanks with an empty user password).

  ConnectorNo auth

• pdf_fillA

  pdfops-mcpA

  Fill AcroForm form fields in a PDF and return the result. Field names must exist in the PDF (use pdf_inspect first). All values are strings; checkboxes take "true"/"false"; dropdown/radio/optionlist values must be one of the field's options; text values must respect the field's maxLength from pdf_inspect. The source PDF is never modified. Returns the filled PDF inline as an application/pdf resource. Encrypted PDFs are rejected with decrypt advice (common for government blanks with an empty user password).

  ConnectorNo auth

• drive_readA

  ecomdlyA

  Read one Google Drive file by id (from drive_search) as text: a Google Doc or Slides as plain text, a Google Sheet as CSV (its first sheet), a text, CSV, JSON, Markdown or XML file as it is. Other files (PDF, images, Office) return their details and link only. Long files are cut; say so when you quote them.

  ConnectorNo auth

• create_upload_linkA

  LivePage · 活页A

  Get an upload page for the user, who picks the files on their phone or computer (PDF / PPTX / images / large files). Which upload route: terminal ⇒ SPACE CLI (create_cli_token first); no terminal and text files up to 2 MB in total ⇒ publish_file; anything else or unsure ⇒ create_upload_link. Use this when you have NO terminal and the page is not text files within 2 MB (PDF, PPTX, images, large files), or when you are not sure: the platform creates an upload page link; give it to the user and they pick the files on their phone (WeChat works) or computer. The link is valid for 2 hours, succeeds only once, uploads only into this one page, and needs no login. To add a version to existing pages pass proposal_id (find it with list_proposals first); to create new pages pass title (optional folder_id). hold defaults to true: after approval the version is NOT released until the user confirms the preview and you call publish_version. After calling, hand the url to the user unchanged, say exactly which file to upload and ask them to come back and say “uploaded” when done; then call get_version with version_id every 15–30 seconds until it is no longer uploading: preview_ready or approved ⇒ give the user the preview URL to confirm; converting ⇒ keep polling; review ⇒ tell the user it is under manual review. After upload, the page also links to the page details for preview and sharing; keep following up through get_version and do not publish a version that is waiting to publish before the user confirms. For a single HTML or Markdown file whose content you already have, use publish_file instead — the user does not need to do anything. Keywords: publish · web page · webpage · link · share · share to WeChat · WeChat link · html · pdf · markdown · upload · LivePage · proposal.

  ConnectorAPI key