Every capability SuperDocs ships.

One API for editing, drafting, searching, summarizing, generating visual content (images, diagrams, drawings, equations), and exporting styled documents — .docx, PDF, HTML, Markdown, plain text. Live in production. Same capabilities over REST and MCP. This page is exhaustive — skip to the group that matches what you're building.

Core editing intelligence

Section-precision editing

The AI changes what you ask for. Nothing else.

Documents load as structured HTML where every paragraph, heading, table, row, and cell carries a unique identifier internally. The AI can target one section without touching anything else — "remove row 3 of the pricing table", "bold the second paragraph in section 4", "replace the governing-law clause" all work as natural-language instructions, even on a 100-page document edited 30 times.

Best for: Long documents, contracts, SOPs, formal reports — anywhere targeted edits matter more than wholesale rewrites.

Style preservation on edit and export

Tables, borders, shading, fonts — all survive every round-trip.

Tables with borders and alternating row shading, merged cells, fonts, font sizes, colors, inline styling, lists, indentation, headers and footers all survive both AI edits and the round-trip to .docx, PDF, or HTML. Most general-purpose AI tools strip or mangle this — SuperDocs is built around preserving it.

Best for: Branded templates, legal documents, formal correspondence — anywhere format fidelity is part of the deliverable.

Document intelligence

Search and summarize at any granularity. Keep several documents open at once, and synthesize across all of them.

Search within documents

Find any clause by topic or keyword. Returns matching sections with context.

Search isn't just full-text matching — the AI understands semantic meaning. Ask "find all indemnity clauses" across a 100-page contract and get back the exact sections, even when they use different wording. Works against the active document or across all attachments at once. Results come back with surrounding context so you can verify the match without opening the file.

Best for: Contract review, compliance audits, extracting specific terms from long documents, finding all references to a concept across multiple files.

Summarize sections on demand

One sentence or one paragraph. You decide the granularity.

Ask "summarize the force majeure section" or "give me a 2-line summary of the payment terms" and the AI extracts just that section, then summarizes it at the level of detail you want. Pair with semantic search — "find and summarize all limitation-of-liability clauses" works as a single instruction. No need to read line-by-line.

Best for: Contract reviews, due diligence, quick understanding of specific parts of long documents, briefing materials.

Summarize entire documents at any length

Executive summary, one-pager, or detailed bullet outline — your call.

Get a concise summary of an entire document at a length you specify. "Executive summary in three sentences", "one-page overview", "detailed bullet-point summary by section" — all work. The AI reads the full document and distills it efficiently. Summaries cover key sections, critical terms, and overall structure. Works on documents up to ~100 pages without context-window pressure.

Best for: Quick understanding of newly-received documents, briefing executives, preparing for negotiations, extracting key terms from regulatory filings.

Multi-document workspace

Open several documents as editable tabs in one chat. Switch focus, edit any of them, create new ones.

Work on more than one document in a single conversation — each opens as its own editable tab, and you switch focus between them with a click. Tell the AI which document to edit ("update the invoice", "now switch to the cover letter"), or ask it to pull content from one into another ("add the summary from the report to a new section in the proposal"). The AI can even spin up a brand-new document in its own tab mid-conversation ("draft the meeting notes in a separate document"). Every tab keeps its own full edit history.

Best for: Drafting a set of related documents together (contract + cover letter + invoice), comparing and porting content side by side, multi-deliverable workflows in one chat.

Durable Files — a reusable document library

Your documents persist across chats. Reopen any of them in any conversation.

Documents you create or upload are saved to a durable Files library — they outlive the chat that made them. Browse everything you've worked on, rename or archive a document, and reopen the same one in any new conversation to keep editing it. Open a saved document in two chats and you're editing the one shared document, not a copy — changes stay in sync. A real document library, not a pile of one-off sessions.

Best for: Teams that revisit the same documents over time, building a reusable library of contracts and templates, picking up a document in a fresh conversation weeks later.

Cross-document reference and synthesis

Reference one document while editing another. Compare, port, align.

With multiple documents and attachments open in a session, the AI references any of them while editing the document you have in focus. "Port the indemnity clause from the attached template into this contract", "compare these two NDAs and align the payment terms", "find clauses in the attached precedent that handle this case better" — all work as natural-language instructions. The AI searches across everything in the session, surfaces matches, and adapts content to the current context.

Best for: Standardizing language across contracts, porting terms from templates, comparing versions, drafting from clause libraries.

Rich editing & formatting

Beyond basic edits — full toolbar, structural hierarchy, table-cell control, page metadata.

Full rich-text formatting toolbar

Bold, italic, underline, colors, highlights, fonts, sizes — and a format painter.

Beyond basic editing — the AI applies bold, italic, underline, strikethrough, text color (10-color palette), text highlight, custom font selection, six preset font sizes (12px–30px), configurable line spacing (single, 1.15, 1.5, double), and text alignment (left, center, right, justify). All preserved on round-trip exports. The format painter copies a style from one selection and applies it to another with a single click — useful for matching styling across a long document.

Best for: Visually distinctive documents, applying brand style guides, adapting documents for different audiences, preserving template styling on edit.

Heading and list hierarchies

H1–H3 headings, bullets, numbered lists, blockquotes, with deep nesting.

Apply heading styles (H1, H2, H3) with hierarchy preserved on export. Create bulleted and numbered lists with automatic numbering. Build deeply nested lists. Convert between bullet and numbered formats by natural-language instruction. Add blockquotes for citations or emphasis. Horizontal rules to divide sections. The AI respects these structures — "convert the first three paragraphs to a bulleted list" works without reformatting surrounding content.

Best for: SOPs, structured documentation, proposals, outlines, academic papers — anywhere hierarchy matters.

Table editing with cell-level control

Insert, merge, split cells. Preserve shading, borders, formatting on edit.

Insert and delete tables and rows. Merge or split cells. Apply alternating row shading. Set border styles. All cell-level operations work via natural language: "merge the first three columns of row 2", "add a row after row 4 with these values", "split the merged cell in A1". Tables survive round-trip to .docx and PDF with formatting intact. Useful for pricing tables, comparison matrices, and any data-heavy document.

Best for: Documents with pricing or data — proposals, contracts with pricing schedules, technical specifications, comparison charts.

Headers, footers, and hyperlinks

Page numbers, document titles, branded headers, hyperlinks — managed via natural language.

Add headers and footers that appear on every page (or specific pages) — page numbers, document titles, company names, dates. Edit existing headers/footers directly. All survives PDF and .docx export. Hyperlinks work the same way: "make this text link to our website" or "remove the broken link in section 4". Both internal document references and external URLs supported.

Best for: Formal business documents, branded templates, compliance documents requiring page numbering, documents with cross-references.

Visual content & media

Generate, edit, and embed images, diagrams, drawings, and equations directly inside your document — all by chatting.

Generate images from a description

"Generate a sunrise over a glass office building" → photorealistic image inserted in place.

Describe the image you want and the AI creates it and inserts it into the document. Photorealistic shots, illustrations, hero images, logos, infographics with text — all by natural-language instruction. The AI picks the right model automatically: a photorealistic image generator by default, and a text-rendering-optimized model for prompts that need legible text on the image (logos, infographics, slide hero shots). Generated images live in the document like any other photo and can be edited, replaced, or removed afterward by chat.

Best for: Marketing pages, proposals, sales decks, blog posts, product specs, anything where finding stock imagery is friction.

Edit any image with natural language

"Brighten this dramatically", "recolor with warm sepia", "crop tightly to the subject", "remove the background".

Click any image in the editor and tell the AI what to change — brighten, darken, contrast, recolor, apply a circular mask (with transparent corners), tight crop to the subject, semi-transparent fade, full background removal — all in plain English. The AI generates new bytes and swaps them in. Subject identity (faces, geometry, branding) is preserved across the edit. Each edit typically takes under a minute. You can iterate ("a bit warmer", "now crop tighter") and use Reset to Original to revert to the original bytes at any time.

Best for: Marketing assets that need to match a campaign, contracts and reports where logos need cleanup, design docs where reference shots need treatment, anywhere a quick photo edit would otherwise mean leaving the document.

Replace an image with an attachment

Attach an updated logo to chat. Tell the AI "use this as the company logo". Done.

Attach a fresh image to chat (the new logo, the updated headshot, the corrected diagram screenshot) and ask the AI to swap it in for an existing image in the document. Pure URL swap — no AI generation cost, no waiting. Works for one-off updates ("replace the cover photo with this") and for recurring patterns where users attach a fresh asset on every iteration.

Best for: Branded templates that need per-customer assets, document workflows where users supply their own imagery, content updates after a rebrand.

Auto-rendered diagrams (Mermaid)

"Make a flowchart of the user signup process" → live, re-editable diagram.

Describe a flowchart, sequence diagram, org chart, ER diagram, mindmap, timeline, or Gantt in plain language and the AI generates the diagram for you; the editor renders it live as a clean SVG. Re-editing is instant and free of regeneration cost — say "add a Police Verification step after Background Check" and the AI rewrites the diagram in place. Diagrams export correctly in PDF and .docx (rendered to image at export time). Full Mermaid syntax catalog supported, including xychart, mindmap, and timeline.

Best for: Technical documentation, process docs, runbooks, architecture overviews, training materials — anywhere a diagram beats a paragraph.

Hand-drawn sketches with a built-in canvas

Click the pencil → draw → save → the sketch is in your doc. Re-open the canvas any time to redraw.

Open a freehand drawing canvas inside the editor — sketch quickly with shapes, arrows, and freehand strokes, save, and the drawing lands in the document as an image. Click it later, hit Redraw, and the canvas reopens with your original strokes so you can tweak them. The same drawing can also be edited as an image via natural language ("turn this rough sketch into a realistic logo") — and the original strokes are still there if you want to redraw from scratch.

Best for: Whiteboarding inside a doc, quick architecture sketches, annotating a screenshot, turning a hand-sketched logo into something polished without leaving the editor.

Math equations (LaTeX / KaTeX)

Inline `$x^2 + y^2 = z^2$` and block equations. Renders in the editor, exports cleanly.

Insert math equations using familiar LaTeX syntax — inline (`$...$`) or block (`$$...$$`). The editor live-renders them with KaTeX. Equations survive .docx and PDF export. The toolbar has an equation button that prompts for LaTeX so you don't have to remember the delimiters; in chat you can also just say "add the quadratic formula here" and the AI will insert the right LaTeX.

Best for: Academic papers, technical reports, finance documents with formulas, engineering specs, anywhere math needs to be written correctly the first time.

Auto-generated table of contents

Insert once. It updates itself as your headings change.

Drop a table of contents block into the document and it auto-populates from your H1/H2/H3 headings. Add a heading later — the TOC updates. Click a TOC entry to jump to that section. Survives export to PDF and .docx (rendered as a list of section titles).

Best for: Long documents, manuals, books, regulatory filings, anything 10+ pages where readers need to navigate.

Knowledge & attachments

Reference files (text or visual). Build institutional memory the AI uses on every edit.

Multimodal vision on attachments

Attach an image. The AI reads it.

Screenshots, scanned forms, diagrams, charts (PNG/JPG/WebP) — the AI interprets them visually while editing the active document. Transcribe a screenshot into structured text, extract numbers from a chart, reference a diagram while drafting documentation, identify entities in a scanned form.

Best for: Workflows that mix text documents with image references — design docs, compliance docs that reference scanned forms, technical writing that references architecture diagrams.

Build a knowledge base from attachments

Upload your templates, style guides, past contracts. The AI references them on edit.

Upload your organization's template library, style guides, past contracts, or SOP documents as attachments. The AI references them automatically when editing the active document — "make this sound like our standard tone", "follow the format of our usual NDAs", "use the indemnity language from our gold-standard contract". Builds an institutional memory that shapes AI behavior. Attachments are scoped per session, so a knowledge-base session can be reused as a starting point and copied for each new document.

Best for: B2B teams with house styles or templates, legal teams with clause libraries, marketing teams with brand voice, compliance teams with corporate policies.

Semantic search across attachments

Upload once. Query any way. The AI understands meaning, not just keywords.

The AI reads and understands every attachment when uploaded — it knows what's in it, not just the words it contains. Ask "find the data processing clause from the attached regulations" and the search returns the matching section even when the attached doc uses entirely different wording. Useful for large attachments (50+ pages) where keyword search would miss relevant sections, and for reference documents you query repeatedly across sessions.

Best for: Reference docs (regulations, industry standards, policy manuals), large attachments queried multiple times, building searchable knowledge over time.

Conversation & robustness

Multi-turn context that holds across days — and, when you turn it on, across chats. Auto-recovery from edits that don't quite fit.

Persistent conversation context

Ask follow-ups. Refine prior edits. Context never resets.

Every message in a session carries the full conversation history. Ask "make that more formal", then "add three paragraphs of detail to what you just wrote", then "change the tone back to friendly" — the AI remembers all prior context, edits, and stated preferences. History persists across server restarts and redeploys. Reload a session weeks later and the AI still has the full context (the document, the attachments, every turn of the conversation, every change made).

Best for: Iterative editing workflows, multi-turn refinements, long-running document projects, anything where the user comes back later.

Cross-session memory and search

Opt in, and the AI carries your preferences and finds your past work across chats.

Turn it on and the AI remembers stated preferences from one conversation to the next — your house style, your preferred tone, the way you like things formatted — instead of relearning them every chat. It can also find and reuse your own past documents and chats: "start this from the proposal I wrote last month", "use the same tone as my last contract". Off by default, and scoped to your account — for B2B platforms, scoped per end customer so one customer's memory never bleeds into another's.

Best for: Power users who reuse a consistent style, teams building on their own past work, B2B platforms that want each end customer to get a personalized assistant.

Automatic error recovery

If something fails, the AI tries again a different way before asking you.

When an edit fails on the first approach (e.g., the section the AI tried to find didn't exist with those exact keywords), it automatically tries broader strategies — semantic search instead of keyword match, alternative phrasings of the user intent, looking in adjacent sections. Retries happen without user intervention. If all approaches genuinely fail, the AI explains what it tried and asks for clarification with specifics rather than a generic error. Dramatically reduces "I didn't understand your request" loops.

Best for: Complex documents with varied terminology, ambiguous instructions, long documents where sections may have been edited since last viewed.

Human control & approval

Decide which changes land, see progress live, keep big-doc edits cheap.

Human-in-the-loop approval

Every change reviewable before it lands.

Set approval_mode='ask_every_time' on chat_async and each proposed change is surfaced as a structured diff (chunk-level before/after HTML + an explanation) for the user to approve, deny, or send back with feedback. Approved changes apply atomically; denied changes leave the document untouched. State persists across server restarts so multi-step approvals survive autoscaling.

Best for: Multi-stakeholder workflows, regulated industries, anywhere the cost of a bad edit landing without review exceeds the cost of a confirmation click.

Per-message chat revert

"Oops, undo that" rewinds chat and document together.

A small "↶ Revert" button under every user message rewinds both the conversation and the document state to the moment right before that message was sent. The reverted message text drops back into the compose box so you can edit and resend with a clearer instruction. The original branch is preserved server-side for audit but hidden from the active timeline. Available in the web app (with a confirmation dialog), via REST (POST /v1/sessions/{id}/revert), and as the revert_session_to_message MCP tool — so AI agents can also undo a step mid-workflow.

Best for: "Oops, undo that AI change" moments, exploring an alternate prompt without starting from scratch, recovering from a misunderstood instruction without losing the rest of your work.

Compact response mode for long sessions

140× token reduction on large-document editing.

On documents larger than ~20 pages, set response_mode='compact' on chat and the response includes only chunk_diffs (per-section before/after for sections that actually changed) instead of the full updated HTML. A 5-turn editing session on a 100-page doc drops from ~650K tokens of response overhead to ~3K. To read sections, just ask in natural language — "show me the force majeure clause" returns the content in the chat reply.

Best for: AI agents editing documents larger than ~20 pages where context window pressure matters.

Real-time progress via SSE

Status bars and live diffs without polling.

Subscribe to /v1/chat/{session_id}/stream for intermediate events while the agent works — "Searching...", "Editing...", proposed-change diffs, document-sync after upload, the final response, usage info, and errors. EventSource auto-reconnects on drop.

Best for: Frontends that show live progress, status bars, or partial results before the full answer is ready.

Multi-format I/O

Six input formats. Five output formats. Same fidelity throughout.

Multi-format input and output

One API. Six input formats. Five output formats. Same fidelity throughout.

Accept .docx, PDF, HTML, Markdown, RTF, or plain text on input. Export the same document as .docx, PDF, HTML, Markdown, or plain text — same parsing pipeline regardless of input. Drop in user files in whatever format they have; deliver in whatever format they need.

Best for: Format conversion workflows, accepting user uploads in any format, delivering in any format your downstream system needs.

Pre-signed URL upload and download

Large files stream straight to storage. Bytes never touch your context.

Files larger than ~100KB use a pre-signed URL flow — the agent gets a short-lived PUT URL plus a ready-to-run curl example, then shells the file directly to cloud storage. Same in reverse for downloads (15-minute GET URLs). Saves a 100-page styled .docx ~70K tokens per upload vs inline base64. Max file size: 100 MB.

Best for: Production AI agents working with real-world document sizes — multi-page contracts, manuals, regulatory filings.

Developer & integration

Reach SuperDocs from any language, any AI client, any cost-conscious workflow.

MCP server — 35 tools + 4 prompts, every major client

One install. Cursor, Claude Code, Claude Desktop, VS Code, Windsurf, Continue, Zed.

All 35 tools + 4 user-invocable workflow prompts exposed as a single Model Context Protocol server at api.superdocs.app/mcp (Streamable HTTP transport). One config entry in your client gives both tools and prompts — Cursor/Claude Code/Desktop users see 4 discoverable slash-command workflow templates (/superdocs:draft_from_outline, /superdocs:edit_styled_docx, /superdocs:convert_format, /superdocs:review_contract_for_redflags) alongside all tools. sk_ Bearer auth, RFC 9728 metadata for OAuth-discovering clients.

Best for: AI-coding-tool users who want SuperDocs available in their editor without writing API integration code.

Three authentication paths

Web users, individual developers, or B2B orgs — same 35 tools.

Firebase tokens for the web app (auto-issued via Google Sign-In or email/password). User API keys (sk_) for individual developers, MCP integrations, scripts. Organization API keys (lce_) for B2B integrations with shared usage limits. All three reach the full REST API and all 35 MCP tools with identical scoping.

Best for: Any combination of web app, individual developer integrations, and B2B partnerships — one platform, three access patterns.

REST API works with any programming language

Python, JavaScript, Go, Ruby, C#, Java, Rust — or curl. No SDK lock-in.

One REST API (50+ endpoints) works with any language that can make HTTP requests. No NPM packages to keep current, no language-specific SDKs to maintain, no framework dependencies to upgrade. Integrate with a few lines of code in whatever language your backend already speaks. Full OpenAPI specification published — generate your own typed client with openapi-generator, Stainless, or any other codegen tool of your choice.

Best for: Polyglot engineering teams, backend services across multiple languages, avoiding SDK lock-in.

Real-time usage tracking and transparency

See your operation count and tokens after every call. No surprise bills.

Every API response includes usage data — operation count consumed, tokens used. The SSE stream emits a usage event after each operation. Your dashboard shows remaining operations in your current tier and resets on your billing cycle. Promo allowances deplete before paid-tier operations so you always burn the cheapest credits first. Full transparency at every step.

Best for: Cost-conscious integrations, monitoring spend, forecasting overage, teams on a budget, self-service deployments at scale.

Scale & operations

Long-lived state, multi-tenant controls, global reach, vertical-platform building blocks.

Sessions and persistence

State that survives restarts. Reload weeks later.

Every conversation is a session_id (a string the caller chooses). The full document state, conversation history, attachments, pending HITL changes, and AI working memory persist across calls and across server restarts. Reload an old session days later and the AI still has the full context.

Best for: Long-running document workflows, async editing where the user comes back hours later, multi-turn editing where state carries between turns.

Async jobs with durable state

Long edits and HITL approvals survive autoscaling, restarts, redeploys.

Long-running edits and HITL workflows return a job_id; the client polls or subscribes to SSE. Job state persists in a database, so any backend instance can pick up a job mid-flight. Approved changes resume automatically — the user can walk away and come back hours later.

Best for: Any workflow that takes more than 30 seconds or needs human approval mid-flight.

Per-organization feature flags

Enable or disable features per customer. One codebase. Many configurations.

B2B deployments can toggle specific features on or off per organization. Offer one platform integration to all customers but let Enterprise org A use a custom branding skin while Startup org B sticks with the default. Different orgs can have different rate limits, feature sets, or experimental rollouts — all from the same codebase, all controlled by API.

Best for: Multi-tenant B2B platforms serving different customer tiers, gradual feature rollouts, enterprise customization without per-customer deployments.

Promo codes and credit allowances

Time-limited operation grants for trials, partnerships, launches.

Issue promo codes that grant temporary operation allowances ("LAUNCH50" = 50 ops valid for 30 days, max 200 redemptions). Users redeem in Settings. Promo operations deplete before paid-tier operations so users get the most out of their allowance. Every redemption is tracked and auditable.

Best for: Product launches, partner programs, customer pilots, trials, conferences, hackathons.

Multi-language editing

Natural-language instructions and document content both work across many languages.

Production users have edited documents in English, Spanish, French, Hebrew, Korean, Mandarin, and others (16+ languages confirmed in real usage so far). Write your prompt in one language, edit a document in another, get the AI's reply in whichever language you wrote the request. Multilingual documents (e.g., bilingual contracts) handled correctly. Tone and formality conventions adapted per language.

Best for: International teams, multilingual document workflows, organizations serving non-English markets, contract translation and adaptation.

Build vertical AI on SuperDocs

Contract AI, Compliance AI, Marketing AI — your domain, our platform.

Combine attachments (your domain knowledge), sessions (long-running workflows), and chat instructions to build domain-specific applications on top of SuperDocs. Contract AI: attach your standard clause library, get an AI that writes contracts in your house style. Compliance AI: attach your regulations, get an AI that audits documents for compliance gaps. Marketing AI: attach your brand voice guides, get an AI that produces on-brand content.

Best for: Vertical SaaS platforms, agencies serving specific industries, organizations with strong domain languages.

See it in your editor in 5 minutes.

Free plan includes 500 AI operations per month. No credit card. Install the MCP server in Claude Code, Cursor, Claude Desktop, or anywhere else and start editing styled documents from your AI tool of choice.

Try It Free MCP Quickstart