AILANG Parse

sunholo-data/ailang-parse

Built by the Sunholo team behind AILANG, this parser extracts structured content from Office documents and PDFs with unusual precision. The deterministic XML approach captures track changes, interleaved comments, headers, footers, and merged cells that most parsers miss. Office formats run locally with zero AI. PDFs and images delegate to whatever model you configure (Gemini, Claude, local Ollama). Outputs JSON and markdown, runs via stdio or HTTP. The team benchmarked it against Pandoc, Docling, and six others on 69 files across 11 formats and scored 93.9% composite. Reach for this when you need redlining metadata, speaker notes from PPTX, or multi-sheet XLSX data without fighting raw OOXML yourself.

tools: 10
auth: Secret needed
transport: STDIO, HTTP
env vars: 2
last updated: Nov 5, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://docparse.ailang.sunholo.com/mcp/connect/ --name parse

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http parse https://docparse.ailang.sunholo.com/mcp/connect/

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 10 tools

Verified live against the running server on Nov 6, 2026.

createUploadGet one-time upload links for files in your sandbox or workspace, when you can run shell commands with network access (Claude Code, Codex, a code sandbox). One token PER FILE: a token uploads exactly one file. For several files set count (1..20) to get that many descriptors in...3 params

Get one-time upload links for files in your sandbox or workspace, when you can run shell commands with network access (Claude Code, Codex, a code sandbox). One token PER FILE: a token uploads exactly one file. For several files set count (1..20) to get that many descriptors in...

Parameters* required

countnumber

filenamestring

mimeTypestring

editDocumentEdit a document: parse it, apply a JSON array of edit deltas, and return the modified blocks (same shape as mcpParse with outputFormat "blocks"). deltas "" or "[]" returns the document unchanged. Office formats only: docx, pptx, xlsx, odt, odp, ods. Give the document ONE way:...7 params

Edit a document: parse it, apply a JSON array of edit deltas, and return the modified blocks (same shape as mcpParse with outputFormat "blocks"). deltas "" or "[]" returns the document unchanged. Office formats only: docx, pptx, xlsx, odt, odp, ods. Give the document ONE way:...

Parameters* required

contentstring

contentEncodingstring

deltasstring

fileobject

fileRefstring

filenamestring

filepathstring

mcpAccountYour AILANG Parse account: plan, monthly usage and limits, your keys, and whether request history is kept. Actions: "status" (default) → plan, usage this month and remaining allowance "keys" → your keys with per-key usage ("usage" is an alias) "history" → whether request histo...1 params

Your AILANG Parse account: plan, monthly usage and limits, your keys, and whether request history is kept. Actions: "status" (default) → plan, usage this month and remaining allowance "keys" → your keys with per-key usage ("usage" is an alias) "history" → whether request histo...

Parameters* required

actionstring

mcpConvertCreate a document in another format: docx, pptx, xlsx, odt, odp, ods, html, md or qmd. To write a new document, write Markdown and send it as content with filename "notes.md" (headings become slides in pptx). To convert an existing document, give it ONE way: fileRef: a file th...8 params

Create a document in another format: docx, pptx, xlsx, odt, odp, ods, html, md or qmd. To write a new document, write Markdown and send it as content with filename "notes.md" (headings become slides in pptx). To convert an existing document, give it ONE way: fileRef: a file th...

Parameters* required

contentstring

contentEncodingstring

fileobject

fileRefstring

filenamestring

inputstring

outputFormat*string

outputPathstring

mcpEstimateEstimate cost and latency for parsing a document. Accepts a file path or sample_id. No auth required.2 params

Estimate cost and latency for parsing a document. Accepts a file path or sample_id. No auth required.

Parameters* required

filepath*string

outputFormat*string

mcpFormatsWhat AILANG Parse can read and write, how to send it a document, and the sample documents you can try without one. No sign-in needed.

What AILANG Parse can read and write, how to send it a document, and the sample documents you can try without one. No sign-in needed.

No parameters. Call it with no arguments.

mcpParseParse a document into structured blocks, Markdown, HTML or A2UI, or a short summary of it. Give the document ONE way: fileRef: an uploaded file (mcp-file://docparse/file_...). The same user can use it again for 30 minutes after the first use (more parts, another format), then...11 params

Parse a document into structured blocks, Markdown, HTML or A2UI, or a short summary of it. Give the document ONE way: fileRef: an uploaded file (mcp-file://docparse/file_...). The same user can use it again for 30 minutes after the first use (more parts, another format), then...

Parameters* required

contentstring

contentEncodingstring

cursorstring

fileobject

fileRefstring

filenamestring

filepathstring

maxCharsstring

outputFormatstring

pdfBackendstring

requestIdstring

submit_feedbackAnonymous bug report / feature request / docs gap, queued for human review. Default routing: `public-feedback` inbox (general AILANG). Pass `package="vendor/name"` (e.g. "sunholo/auth") to route to that package's `pkg:vendor/name` inbox where its autonomous agent watches. Cate...8 params

Anonymous bug report / feature request / docs gap, queued for human review. Default routing: `public-feedback` inbox (general AILANG). Pass `package="vendor/name"` (e.g. "sunholo/auth") to route to that package's `pkg:vendor/name` inbox where its autonomous agent watches. Cate...

Parameters* required

ailang_version*string

The reporter's CLI version (free-form, used for triage)

auto_dispatchboolean

Authorize the receiving package's autonomous agent to act on this submission. Default false (files for human triage). Tagged on the Pub/Sub notification as category=auto:<original> for coordinator...

body*string

Full description (≤10 KB)

category*string

bug | feature | docs | limitation

contactstring

Optional follow-up address (free-form, opaque to the server)

packagestring

Optional vendor/name (e.g. "sunholo/auth") to route to that package's pkg:vendor/name inbox. Empty = general AILANG feedback.

snippetstring

Optional code/error snippet (≤4 KB)

title*string

Short title for the report

uploadDocumentLet the user pick a file to parse: shows the AILANG Parse card with a Choose file button. The card uploads the file and tries to summarise it for you; either way you get its fileRef. Then call mcpParse with that fileRef for the content (the same user can reuse it for 30 minute...1 params

Let the user pick a file to parse: shows the AILANG Parse card with a Choose file button. The card uploads the file and tries to summarise it for you; either way you get its fileRef. Then call mcpParse with that fileRef for the content (the same user can reuse it for 30 minute...

Parameters* required

outputFormatstring

uploadViaHostReceive a file from the AILANG Parse upload widget, relayed by the host as base64. Only the widget calls this; ticket is the upload token it holds.3 params

Receive a file from the AILANG Parse upload widget, relayed by the host as base64. Only the widget calls this; ticket is the upload token it holds.

Parameters* required

base64*string

filename*string

ticket*string

Configuration

DOCPARSE_API_KEYsecret

AILANG Parse API key (dp_...). Optional — the bridge auto-loads keys saved at ~/.config/ailang-parse/credentials.json. Get one from https://www.sunholo.com/ailang-parse/

AILANG_PARSE_MCP_URL

Override the hosted MCP endpoint. Defaults to https://docparse.ailang.sunholo.com/mcp/