The API MCP server,
connected in one click.

“Use “document.extract_text”: Extract plain text from a PDF or image (base64-encoded). Use when you need raw text for downstream AI analysis (summarization, claim checkin.”

“Use “document.extract_tables”: Extract tables and forms as Markdown from a PDF or image (base64-encoded). Use when the document contains structured tabular data such as fi.”

“Use “document.parse_invoice”: Parse a receipt or invoice document into structured fields. Uses a quality AI model for accuracy. Use when you need to extract line items, t.”

“Use “document.check_claims”: Verify a list of factual claims against document text. Uses a quality AI model with citation-level evidence. Use after document.extract_text.”

document.extract_text — Extract plain text from a PDF or image (base64-encoded). Use when you need raw text for downstream AI analysis (summarization, claim checkin

document.extract_tables — Extract tables and forms as Markdown from a PDF or image (base64-encoded). Use when the document contains structured tabular data such as fi

document.parse_invoice — Parse a receipt or invoice document into structured fields. Uses a quality AI model for accuracy. Use when you need to extract line items, t

document.check_claims — Verify a list of factual claims against document text. Uses a quality AI model with citation-level evidence. Use after document.extract_text

document.extract_structured — Extract typed fields from document text using a caller-defined schema. Uses a quality AI model with retry logic. Use when you need specific

document.summarize — Summarize document text into a prose summary and key points with citations. Use after document.extract_text or url.extract when you need a c

bundle.verify — Verify the cryptographic integrity of an evidence bundle (ev_...) owned by your API key. Checks manifest hash, EIP-191 signature, and R2 art

collection.create — Create a named document collection for cross-document semantic search and RAG-based Q&A. Free — no credits consumed. Use when you want to gr