{"uid":"cap_gRKpezzYriFiWg-RmCE6j","slug":"pdf-metadata-extractor-ebd194cf","name":"PDF Metadata Extractor","description":"PDF metadata from a URL: page count (from page objects), PDF version, title, author, subject, creator/producer, creation and modification dates from the Info dictionary or XMP, encryption flag, and byte size. Reads the first 2 MB, so counts for very large PDFs may be partial (flagged). $0.01 per document.","url":"https://intel.rallylive.ca/dev/pdf-meta","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_sOLP1B5dgrkY28mlZXo0H","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts metadata from a PDF document at a given URL, including page count, PDF version, title, author, creation dates, encryption status, and file size.","exampleAgentPrompt":"Can you pull the metadata from this PDF — https://example.com/report.pdf — and tell me the page count, who created it, what PDF version it is, and whether it's encrypted?","exampleUseCases":[{"title":"Auditing uploaded contract PDFs","prompt":"I need to verify the metadata of this contract PDF at https://docs.example.com/contract-2024.pdf — specifically who authored it, when it was created and last modified, and whether it's encrypted."},{"title":"Checking page count before processing","prompt":"Before I process this document, can you check how many pages are in the PDF at https://files.example.com/annual-report.pdf and what its file size is?"},{"title":"Verifying PDF provenance for compliance","prompt":"For compliance purposes, I need to know the creator, producer, creation date, and PDF version of the document at https://storage.example.com/submission.pdf — can you fetch that metadata?"}],"resultDescription":"Returns a structured object containing: page count (may be partial for PDFs over 2 MB, flagged accordingly), PDF version string, Info dictionary fields (title, author, subject, creator, producer), creation and modification dates (from Info dictionary or XMP metadata), a boolean encryption flag, and the document's byte size.","failureModes":["URL is not reachable or returns a non-200 HTTP status","URL does not point to a valid PDF file","PDF is heavily encrypted and metadata cannot be read","PDF exceeds 2 MB — page count may be partial and is flagged as such","Malformed or corrupt PDF structure prevents parsing","Network timeout when fetching the remote document"],"whenToPreferThis":"Use this endpoint when you need lightweight, fast metadata inspection of a PDF without downloading or fully parsing the entire file. It is ideal for pre-processing pipelines that need page counts, authorship, or date info before deciding how to handle a document. Prefer it over full-document parsers when you only need document properties, not content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:39:47.210Z","isFirstParty":false}