# AILANG Parse

> Universal document parser. Deterministic Office (DOCX/PPTX/XLSX/ODT/ODP/ODS/HTML/MD/CSV/EPUB/EML) in milliseconds, AI-powered for PDFs, images, audio, and video. One block schema for every format. Available as a hosted MCP server, a local MCP stdio server, and a REST API.

This file follows the [llmstxt.org](https://llmstxt.org) convention. Agents should fetch [llms-full.txt](llms-full.txt) for the complete agent-oriented reference (device auth flow, tool catalog, REST examples).

## Essentials

- **Hosted MCP endpoint**: `https://docparse.ailang.sunholo.com/mcp/` (Streamable JSON-RPC, requires API key for parse/convert/account)
- **Hosted REST API**: `https://docparse.ailang.sunholo.com/api/v1/*`
- **Auth**: RFC 8628 device authorization. Call `mcpAuth` → human approves in browser → poll `mcpAuthPoll` → store the returned `dp_…` API key.
- **Discovery**: Call `mcpFormats` (no auth) for the full service contract — formats, samples, pricing tiers, capabilities.

## Docs

- [llms-full.txt](llms-full.txt): full agent reference (auth flow, all 7 tools with params, REST fallback, env vars)
- [mcp.html](mcp.html): human-readable MCP server documentation
- [api.html](api.html): REST API reference
- [pricing.html](pricing.html): pricing tiers
- [GitHub repo](https://github.com/sunholo-data/ailang-parse): source, examples, SDKs

## Optional

- [docs.html](docs.html): full documentation index
- [why.html](why.html): why deterministic Office parsing matters
- [benchmarks.html](benchmarks.html): OfficeDocBench results vs Docling, LlamaParse, MarkItDown