Connects Claude to Google Document AI for OCR and structured data extraction from PDFs and scanned documents. Exposes a docu_scan_extract operation that pulls full text, detects entities, signatures, stamps, and handwriting. Each call consumes one scan credit from your quota. Runs on streamable-http transport and authenticates with a bearer token from spocont.com. Free trial available to test extraction quality before committing to a paid tier. Useful when you need to parse invoices, contracts, or forms and feed the structured output into downstream workflows like accounting systems or databases.
Public tool metadata for what this MCP can expose to an agent.
docu_scan_extractExtract a specific value from a PDF document using Google Document AI. Provide the base64-encoded PDF and describe what label/field you want to find (e.g. "invoice total", "lease start date", "coupon rate"). Returns targetFindings (anchored match), otherFindings (full key-valu...6 paramsExtract a specific value from a PDF document using Google Document AI. Provide the base64-encoded PDF and describe what label/field you want to find (e.g. "invoice total", "lease start date", "coupon rate"). Returns targetFindings (anchored match), otherFindings (full key-valu...
doc_idstringval_typestringnumeric · stringend_anchorstringpdf_base64stringstart_anchorstringfindTheValueWithThisLabelstringdocu_scan_statusCheck remaining scan credits for the current user. Free — does not consume a credit. Call this before a batch of extractions to confirm sufficient quota.Check remaining scan credits for the current user. Free — does not consume a credit. Call this before a batch of extractions to confirm sufficient quota.
No parameter schema in public metadata yet.
csoai-org/pdf-document-mcp
xt765/mcp-document-converter
io.github.xjtlumedia/markdown-formatter
io.github.ai-aviate/better-notion
suekou/mcp-notion-server
meterlong/mcp-doc