{"slug":"well-010-docx-to-text-mmelnyk2000-workers-dev-mcp-07506c","title":"Extract text and tables from a Word .docx file ($0.005 USDC via x402)","host":"well-010-docx-to-text.mmelnyk2000.workers.dev","method":"GET","resource":"https://well-010-docx-to-text.mmelnyk2000.workers.dev/mcp#docx-to-text#docx-to-text","category":"search","description":"Extract text and tables from a Word .docx file ($0.005 USDC via x402). Input: a public https url to a .docx, or docx_base64. https only — http, file, data, localhost, and private IPs are rejected. Caps: 10 MB file, ~15s timeout, max 5 redirects. Tables appear as [table N] placeholders in text. Unico","price_listed":0.005,"price_asked":null,"state":"no_terms","state_label":"Answers HTTP 406 without x402 payment terms","checks_7d":1,"answered_7d":0,"latency_ms_median":null,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"description":"Extract text and tables from a Word .docx file ($0.005 USDC via x402). Input: a public https url to a .docx, or docx_base64. https only — http, file, data, localhost, and private IPs are rejected. Caps: 10 MB file, ~15s timeout, max 5 redirects. Tables appear as [table N] placeholders in text. Unicode dashes/minus signs normalized to '-'. Old binary .doc files are not supported. Returns JSON { file, url, final_url, type: 'docx', text, tables: [{ rows }], warnings }.","example":{"url":"https://example.com/report.docx"},"inputSchema":{"properties":{"docx_base64":{"description":"Alternative to url: the .docx file bytes, base64-encoded (max 10 MB).","type":"string"},"filename":{"description":"Optional file name echoed back as `file`.","type":"string"},"url":{"description":"https URL of a .docx file. http/file/data/localhost/private IPs rejected.","type":"string"}},"type":"object"},"toolName":"docx-to-text","transport":"streamable-http","type":"mcp"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"description":{"type":"string"},"example":{"type":"object"},"inputSchema":{"type":"object"},"toolName":{"type":"string"},"transport":{"enum":["streamable-http"],"type":"string"},"type":{"const":"mcp","type":"string"}},"required":["type","toolName","inputSchema"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-18","reachable":true,"status":406,"valid_402":false,"asked_usdc":null,"price_match":null,"latency_ms":400,"error":null}],"description_full":"Extract text and tables from a Word .docx file ($0.005 USDC via x402). Input: a public https url to a .docx, or docx_base64. https only — http, file, data, localhost, and private IPs are rejected. Caps: 10 MB file, ~15s timeout, max 5 redirects. Tables appear as [table N] placeholders in text. Unicode dashes/minus signs normalized to '-'. Old binary .doc files are not supported. Returns JSON { file, url, final_url, type: 'docx', text, tables: [{ rows }], warnings }.","last_updated":"2026-10-16T00:02:50.314Z","schemes":["exact"]}