# SuperDocs

## Docs

- [Overview](https://docs.typebar.ai/introduction/overview.md): SuperDocs is an AI document editing platform. Edit, create, search, and manage documents through a REST API or MCP.
- [Quickstart](https://docs.typebar.ai/introduction/quickstart.md): Get your API key and make your first SuperDocs API call in under 5 minutes.
- [For AI Agents](https://docs.typebar.ai/introduction/agent-signup.md): Sign up and get a working SuperDocs API key in one call, with no human in the loop.
- [Features](https://docs.typebar.ai/features.md): Comprehensive capability reference for SuperDocs — every shipped feature, grouped by what you'd reach for it for.
- [Account Setup](https://docs.typebar.ai/account/account-setup.md): Create a SuperDocs account, verify your email, and manage your profile.
- [API Keys](https://docs.typebar.ai/account/api-keys.md): Create, manage, and revoke API keys for programmatic access to SuperDocs.
- [MCP Setup](https://docs.typebar.ai/account/mcp-setup.md): Generate an MCP key from the SuperDocs Settings page and connect your AI tool.
- [Plans & Usage](https://docs.typebar.ai/account/plans-and-usage.md): Subscription tiers, operation limits, what counts as an operation, and how to track usage.
- [Billing](https://docs.typebar.ai/account/billing.md): Upgrade your plan, manage your subscription, and cancel from the SuperDocs Settings page.
- [Sessions](https://docs.typebar.ai/concepts/sessions.md): Sessions persist conversation history and document state across requests. You choose the session ID.
- [Documents](https://docs.typebar.ai/concepts/documents.md): Load documents from files, edit them with AI, create new ones from scratch, and export as Word files.
- [Files (durable documents)](https://docs.typebar.ai/concepts/files.md): Documents persist across sessions, so you can list, open, rename, and archive them — and reopen a saved document in any new session.
- [Cross-session memory & search](https://docs.typebar.ai/concepts/cross-session-context.md): Let the AI remember your preferences across chats and reuse your own prior documents — opt-in, off by default, and scoped to you.
- [Attachments](https://docs.typebar.ai/concepts/attachments.md): Upload PDF, DOCX, HTML, text, and image files to give the AI additional context or load them into the editor.
- [Templates](https://docs.typebar.ai/concepts/templates.md): Upload reusable document templates that the AI can search and apply when creating content.
- [Integration Starter Prompt](https://docs.typebar.ai/guides/integration-starter-prompt.md): Paste this into your coding agent to integrate SuperDocs into any product, in any stack, with any architecture. Target fill time: under 5 minutes.
- [SSE Streaming](https://docs.typebar.ai/guides/streaming.md): Stream real-time progress updates from the AI using Server-Sent Events (SSE).
- [Async Jobs](https://docs.typebar.ai/guides/async-jobs.md): Use async chat requests with job polling for long-running operations and background processing.
- [Human-in-the-Loop](https://docs.typebar.ai/guides/human-in-the-loop.md): Review and approve AI-proposed document changes before they're applied, using the HITL approval workflow.
- [Multi-Document Sessions](https://docs.typebar.ai/guides/multi-document.md): Work with several open documents in one session — target any of them by id, let the AI move content between them, or have it open a brand-new document.
- [Concurrent & Cross-Session Editing](https://docs.typebar.ai/guides/concurrent-editing.md): Keep a document in sync when more than one place edits it at once — two browser sessions, a UI tab plus a background job, or any writer-plus-poller pair. Poll for other sessions' edits, autosave human typing, and merge instead of clobbering.
- [Editor Integration](https://docs.typebar.ai/guides/editor-integration.md): Make any rich-text editor round-trip SuperDocs document IDs, so surgical edits work reliably. Drop-in snippets for ProseMirror, TipTap, Slate, Lexical, Quill, and CKEditor 5.
- [Agent Tool Integration](https://docs.typebar.ai/guides/agent-tool-integration.md): Register SuperDocs as a tool in your existing AI agent's tool registry — OpenAI function-calling, Anthropic tool_use, LangChain, LlamaIndex, or any function-calling-compatible framework. Your AI is the consumer; SuperDocs is the document-editing capability it can call.
- [Agent Editing Playbook](https://docs.typebar.ai/guides/agent-editing-playbook.md): How an AI agent edits documents reliably on SuperDocs: choosing the right operation, section rewrites, cheap verification, placement, page breaks, and budgeting operations.
- [Server Integration](https://docs.typebar.ai/guides/server-integration.md): Use SuperDocs from a backend service with no UI — batch document processing, queue workers, scheduled jobs, document workflows. No frontend, no SSE consumer, no human approval needed.
- [Model Selection](https://docs.typebar.ai/guides/model-selection.md): Choose from four AI model tiers and three thinking depths to balance speed, capability, and cost.
- [AI-to-AI Integration](https://docs.typebar.ai/guides/ai-to-ai.md): Connect your AI agent to SuperDocs for autonomous document editing without a browser.
- [MCP Setup](https://docs.typebar.ai/mcp/setup.md): Connect AI tools like Claude Desktop, Cursor, and VS Code to SuperDocs using the Model Context Protocol (MCP).
- [SuperDocs Plugin](https://docs.typebar.ai/mcp/plugin.md): The official Claude Code plugin — single install bundles 38 MCP tools, 4 workflow prompts, and the auto-loading skill.
- [Claude Code](https://docs.typebar.ai/mcp/claude-code.md): Connect SuperDocs to Claude Code (CLI) with a single command.
- [Claude Desktop](https://docs.typebar.ai/mcp/claude-desktop.md): Step-by-step guide to connect SuperDocs to Claude Desktop via MCP.
- [Cursor & VS Code](https://docs.typebar.ai/mcp/cursor-vscode.md): Connect SuperDocs to Cursor, VS Code, or Windsurf via MCP configuration.
- [Available Tools](https://docs.typebar.ai/mcp/available-tools.md): All 38 MCP tools available when connecting to the SuperDocs MCP server.
- [Error Codes](https://docs.typebar.ai/errors/error-codes.md): HTTP status codes, error response format, and common error scenarios for the SuperDocs API.
- [Rate Limits](https://docs.typebar.ai/errors/rate-limits.md): Operation limits per subscription tier, overage pricing, and how to handle 429 responses.
- [Python Examples](https://docs.typebar.ai/examples/python.md): Complete working Python examples for the SuperDocs API using the requests library.
- [JavaScript Examples](https://docs.typebar.ai/examples/javascript.md): Complete working JavaScript examples for the SuperDocs API using fetch and EventSource.
- [curl Examples](https://docs.typebar.ai/examples/curl.md): Copy-paste ready curl commands for every key SuperDocs API operation.
- [Edit, draft, or restructure a document using natural language. Preserves tables, styling, and formatting.](https://docs.typebar.ai/api-reference/v1/edit-draft-or-restructure-a-document-using-natural-language-preserves-tables-styling-and-formatting.md): Synchronous AI chat that can rewrite specific paragraphs, add or remove table rows, restructure sections, generate new content from templates, or transform an entire document. Pass document_html only to load or replace the document; once a session holds a document the server persists it across turns…
- [List your active document editing sessions to resume or audit prior work.](https://docs.typebar.ai/api-reference/v1/list-your-active-document-editing-sessions-to-resume-or-audit-prior-work.md): Returns sessions sorted by most recent activity, with message counts and last-updated timestamps. Each session represents one document with full edit history and AI conversation persisted server-side. Use to find a previous editing context to resume (then call get_session_history) or to audit your w…
- [List your saved documents (the Files view).](https://docs.typebar.ai/api-reference/v1/list-your-saved-documents-the-files-view.md): List the authenticated user/org's saved documents, most-recently-updated first (metadata only — no document content). Each carries a session_count ("N chats"). Documents become durable + reusable automatically as you create or edit them; on the FIRST call we also one-time import the documents of pre…
- [Clear your cross-session memory note.](https://docs.typebar.ai/api-reference/v1/clear-your-cross-session-memory-note.md): Delete the caller's cross-session memory note. Owner-scoped: a caller can only clear its OWN note. With no key this clears the account-level note; with a memory_key it clears that one end-customer's note. Idempotent (removed=0 if it didn't exist).
- [Get a saved document's detail, structure outline, and the chats that used it.](https://docs.typebar.ai/api-reference/v1/get-a-saved-documents-detail-structure-outline-and-the-chats-that-used-it.md): One saved document's metadata plus a STRUCTURE outline and the chat sessions that have it open (prior-chats-per-file). Owner-scoped — 404 if the document isn't yours.
- [Delete (archive) a saved document.](https://docs.typebar.ai/api-reference/v1/delete-archive-a-saved-document.md): Soft-archive a saved document — it leaves the Files view but is recoverable server-side. Presence-aware: if the document is currently open in ANOTHER session and `force` is not set, the request FAILS honestly with HTTP 409 (`code:"document_in_use"` + `open_in_sessions:N` + `suggested_action`) so cal…
- [Rename a saved document and/or update its out-of-flow parts (headers, footers, footnotes, endnotes, comments, sections).](https://docs.typebar.ai/api-reference/v1/rename-a-saved-document-andor-update-its-out-of-flow-parts-headers-footers-footnotes-endnotes-comments-sections.md): Rename one of your saved documents and/or update its out-of-flow parts. Parts are the document's out-of-flow content — headers/footers, footnote and endnote bodies, comments, and per-section page geometry. Every fragment is sanitized on write, writes are versioned and safe under concurrent editors,…
- [Restore (un-archive) a previously archived document by its id.](https://docs.typebar.ai/api-reference/v1/restore-un-archive-a-previously-archived-document-by-its-id.md): Restore (un-archive) a saved document by its id — the mirror of archive_document. The document re-enters your Files view and can be opened/edited again (open it into a chat with open_documents). `document_id` is the same id used by list_documents / archive_document. Idempotent: restoring an already-…
- [Open saved documents into a chat session (shared, never copied).](https://docs.typebar.ai/api-reference/v1/open-saved-documents-into-a-chat-session-shared-never-copied.md): Load one or more SAVED documents into a session as editable tabs. The SAME durable document is attached (never copied), so edits flow back to the one shared row with cross-session soft-collaboration. The first listed document is focused. Returns the refreshed document roster so the client can render…
- [Start a new chat session and open documents into it in one call.](https://docs.typebar.ai/api-reference/v1/start-a-new-chat-session-and-open-documents-into-it-in-one-call.md): Create a session AND open N saved documents into it in ONE call (the documents are SHARED, never copied — the same cross-session behavior as /documents/open). The web UI passes its own session_id so its session model stays consistent; an MCP/API integrator can omit it and the server mints one — the…
- [Persist a user-edited document (non-AI autosave).](https://docs.typebar.ai/api-reference/v1/persist-a-user-edited-document-non-ai-autosave.md): Persist a HUMAN-edited document — the editor's debounced autosave + save-on-blur — WITHOUT an AI turn. Re-indexes the html into the target document (preserving its durable identity so it UPDATES the same Files entry), then saves it so pure typing is preserved AND other sessions with the same documen…
- [Restore a document another session archived, keeping your current edits (web app).](https://docs.typebar.ai/api-reference/v1/restore-a-document-another-session-archived-keeping-your-current-edits-web-app.md): Restore (un-archive) a document that was archived, re-linking it to this session and bringing its content back. `document_id` is the session-local id (same as /save); the durable id is recovered from the cached document. Idempotent: restoring an already-active (or never-archived) document is a no-op…
- [Open a new blank document as a tab in the session.](https://docs.typebar.ai/api-reference/v1/open-a-new-blank-document-as-a-tab-in-the-session.md): Open a fresh BLANK document as a new focused tab in the session (the tab-strip "+"). Non-billable — no AI, no upload pipeline; it is saved on first edit. REST-only (a manual UI affordance, not an MCP tool — agents create documents through chat).
- [List the documents open in a multi-document session.](https://docs.typebar.ai/api-reference/v1/list-the-documents-open-in-a-multi-document-session.md): Returns the editable documents open in this session (focused first), each with its id, chunk count, and focused flag — so a client can render document tabs. The response is token-light by default; pass include_html=true to also get each document's reassembled HTML.
- [Session Document Events](https://docs.typebar.ai/api-reference/v1/session-document-events.md): Poll for cross-session document updates: returns `document_updated` events for documents THIS session holds that OTHER sessions committed since `after_id`. The client polls this (~every 1-2s while a doc is open) and re-fetches the changed document's content so all open sessions converge without a re…
- [Switch which document is focused in a multi-document session.](https://docs.typebar.ai/api-reference/v1/switch-which-document-is-focused-in-a-multi-document-session.md): Make document_id the focused document (the editor's active document and the default edit target). Accepts either the session slot id OR the durable documents.id UUID (the id shown by list_documents/Files). Persists the outgoing focused document into the session's document map and returns the now-foc…
- [Close (remove) a document from a multi-document session.](https://docs.typebar.ai/api-reference/v1/close-remove-a-document-from-a-multi-document-session.md): Remove document_id from the session's open documents (the tab close button). If it's the focused document, focus another open document — `next_focus` if it's still open (so the client can pick the adjacent tab), else the next remaining one; closing the last document leaves the session empty. Returns…
- [Re-apply the AI's intended edit on top of the user's current version of one section.](https://docs.typebar.ai/api-reference/v1/re-apply-the-ais-intended-edit-on-top-of-the-users-current-version-of-one-section.md): Resolve a concurrent-edit conflict on ONE section. When a user edited a section while the AI was also changing it, this re-applies the AI's intended change on top of the user's current text (mode="redo"), or blends the user's and AI's versions into one (mode="merge"). Returns only the rewritten sect…
- [Restore the full conversation and document state for a previous session.](https://docs.typebar.ai/api-reference/v1/restore-the-full-conversation-and-document-state-for-a-previous-session.md): Returns complete message history (user and AI), final document HTML with chunk IDs preserved, attachment list, and editor actions (font, color, alignment changes). Use to continue editing a document you started in a prior session. The AI rehydrates with full context of all prior decisions, chunk IDs…
- [Rewind a chat session to before a specific user message — restores both the document and the conversation in one call.](https://docs.typebar.ai/api-reference/v1/rewind-a-chat-session-to-before-a-specific-user-message-—-restores-both-the-document-and-the-conversation-in-one-call.md): Rewinds a chat session to the state immediately before a specific user message. The document, conversation history, and supporting context all snap back to that point. The text of the reverted message is returned (compose_text) so the caller can edit and resend it. Messages from the reverted turn fo…
- [Undo a revert: restore the pre-revert state and the rolled-back turns.](https://docs.typebar.ai/api-reference/v1/undo-a-revert:-restore-the-pre-revert-state-and-the-rolled-back-turns.md): Revert is non-destructive: this restores the session FORWARD to the pre-revert state (returned by the revert as redo_checkpoint_id), restores the document to that state while still merging any concurrent edits from other sessions (keeping both where they conflict), and un-archives exactly the chat t…
- [Upload Attachment](https://docs.typebar.ai/api-reference/v1/upload-attachment.md): Upload a document attachment to a session for AI reference.
- [Remove an attachment from a session or cancel its in-progress processing.](https://docs.typebar.ai/api-reference/v1/remove-an-attachment-from-a-session-or-cancel-its-in-progress-processing.md): Removes the attachment from the session; the AI will no longer reference it in subsequent chat turns. If processing is still in progress, also cancels the underlying job. Use to free up context, remove sensitive files mid-session, or replace a stale reference document. The attachment_id can be eithe…
- [Check processing status of all attachments in a session.](https://docs.typebar.ai/api-reference/v1/check-processing-status-of-all-attachments-in-a-session.md): Returns each attachment's processing state (pending/processing/completed/failed) plus extracted text length and chunk count once ready. Poll this after upload_attachment_base64 to know when an attachment becomes queryable by the AI. Surfaces processing errors with actionable messages.
- [Upload Document To Editor](https://docs.typebar.ai/api-reference/v1/upload-document-to-editor.md): Upload a document file and load it into the editor.
- [Upload an image and get back a stable URL the editor can drop into <img src>.](https://docs.typebar.ai/api-reference/v1/upload-an-image-and-get-back-a-stable-url-the-editor-can-drop-into-<img-src>.md): Upload a single inline image and return a stable URL you can reference in the document via <img src="...">.
- [Upload a base64-encoded image and get back a stable URL to embed in a document via <img src>.](https://docs.typebar.ai/api-reference/v1/upload-a-base64-encoded-image-and-get-back-a-stable-url-to-embed-in-a-document-via-<img-src>.md): Upload an image (base64-encoded) and get a stable public URL to reference in a document via <img src="...">.
- [Request higher document/chat scale limits in one call — no email needed.](https://docs.typebar.ai/api-reference/v1/request-higher-documentchat-scale-limits-in-one-call-—-no-email-needed.md): Request a higher scale limit for your account in ONE call.
- [Export the current document as a styled .docx (default), .pdf, .html, .md, or .txt file with full fidelity.](https://docs.typebar.ai/api-reference/v1/export-the-current-document-as-a-styled-docx-default-pdf-html-md-or-txt-file-with-full-fidelity.md): Round-trips the document through the original docx renderer, preserving tables, borders, shading, alternating row colors, headers, footers, fonts, inline styling, and embedded images. Two modes: pass html directly to export ad-hoc content, OR pass session_id to export the session's current state. Fo…
- [Request Large Export Email](https://docs.typebar.ai/api-reference/v1/request-large-export-email.md): Enqueue a large-export job — runs in the background and emails a secure, time-limited download link when the export finishes. 24h SLA promised in the email.
- [Upload .docx/PDF/HTML/MD/RTF as the active editable document with chunk-ID structural editing.](https://docs.typebar.ai/api-reference/v1/upload-docxpdfhtmlmdrtf-as-the-active-editable-document-with-chunk-id-structural-editing.md): Parses the file into structured HTML where every paragraph, heading, table, row, and cell has a unique chunk ID, enabling the AI to make targeted structural edits via chat ("remove row 3 of the pricing table" works). Tables, borders, shading, alternating row colors, fonts, and inline styling are pre…
- [Upload a reference file (PDF/DOCX/image) for the AI to query while editing.](https://docs.typebar.ai/api-reference/v1/upload-a-reference-file-pdfdocximage-for-the-ai-to-query-while-editing.md): Files are processed asynchronously and become AI-searchable once ready. The AI can then reference the attachment's content during chat (e.g., "rewrite section 3 to match the style guide PDF I attached"). Images are queryable via multimodal vision. Poll get_attachment_status to know when ready. Disti…
- [Save a document template (NDA, contract, SOP, letterhead) for reuse across sessions.](https://docs.typebar.ai/api-reference/v1/save-a-document-template-nda-contract-sop-letterhead-for-reuse-across-sessions.md): Templates persist across sessions and can be referenced by the AI when drafting new documents (e.g., "draft an NDA using my standard template"). Stored at user or organization scope. Ideal for boilerplate, branded letterheads, recurring document structures, or compliance-required templates. Supports…
- [List your async chat jobs (in-progress, awaiting approval, completed, failed).](https://docs.typebar.ai/api-reference/v1/list-your-async-chat-jobs-in-progress-awaiting-approval-completed-failed.md): Returns jobs sorted by most recent, optionally filtered by status. Use to monitor long-running AI edits started via chat_async, see which jobs are paused waiting for human approval, or audit completed work. Each job tracks the chat that started it, the changes made, and any HITL decisions logged.
- [Get the status, partial results, and any pending changes for an async chat job.](https://docs.typebar.ai/api-reference/v1/get-the-status-partial-results-and-any-pending-changes-for-an-async-chat-job.md): Returns the job's current state (pending, in_progress, awaiting_approval, completed, failed, or cancelled), intermediate AI responses streamed during execution, the final document HTML once complete, and any pending changes awaiting user approval (with chunk IDs and proposed HTML diffs in metadata.p…
- [Cancel a pending or in-progress async chat job.](https://docs.typebar.ai/api-reference/v1/cancel-a-pending-or-in-progress-async-chat-job.md): Stops the AI mid-edit. Already-applied changes are preserved in the document; pending changes are discarded. Use to abort long-running operations that are no longer needed (e.g., user changed their mind, or you want to retry with different parameters or model_tier). Only jobs with status pending or…
- [List all async chat jobs for a specific session, most recent first.](https://docs.typebar.ai/api-reference/v1/list-all-async-chat-jobs-for-a-specific-session-most-recent-first.md): Returns the full job history of one document. Useful for auditing what the AI did to a document over time, or finding a specific job that's waiting for HITL approval. Same shape as list_jobs but scoped to one session.
- [Start a long-running or HITL-approved AI edit; returns a job_id to poll for results.](https://docs.typebar.ai/api-reference/v1/start-a-long-running-or-hitl-approved-ai-edit;-returns-a-job_id-to-poll-for-results.md): Use instead of chat when (a) the edit is large or multi-step, (b) you need human approval on each proposed change before it applies (set approval_mode='ask_every_time'), or (c) you can't afford to block on a synchronous response. To replace the whole document with EXACT content you already hold, pas…
- [Stream Chat Progress](https://docs.typebar.ai/api-reference/v1/stream-chat-progress.md): Stream real-time progress for a chat job using Server-Sent Events (SSE).
- [Approve or deny AI-proposed document changes one-by-one or in batch (HITL workflow).](https://docs.typebar.ai/api-reference/v1/approve-or-deny-ai-proposed-document-changes-one-by-one-or-in-batch-hitl-workflow.md): Used with chat_async when approval_mode='ask_every_time'. For each proposed change (with chunk_id and HTML diff), respond approved=true|false plus optional feedback for the AI to revise on. Approved changes apply atomically; denied changes are discarded; the AI may revise based on feedback in the ne…
- [Resume or stop a chat turn paused by a large-edit continue prompt.](https://docs.typebar.ai/api-reference/v1/resume-or-stop-a-chat-turn-paused-by-a-large-edit-continue-prompt.md): Used with chat_async when a large edit paused to ask whether to keep going. Poll get_job until status=awaiting_approval AND metadata.awaiting_kind='continue_prompt'; then POST here with continue=true to resume (the AI picks up where it left off with a fresh time/step budget) or continue=false to sto…
- [Poll Session Updates](https://docs.typebar.ai/api-reference/v1/poll-session-updates.md): Long-poll for real-time job updates on a session (B2B organizations only).
- [Upload User Template](https://docs.typebar.ai/api-reference/v1/upload-user-template.md): Upload a document file as a personal/organization template.
- [List all saved document templates available to the user or organization.](https://docs.typebar.ai/api-reference/v1/list-all-saved-document-templates-available-to-the-user-or-organization.md): Returns active (non-deleted) templates with name, format, size, and creation date metadata. Use to show the AI what reusable document structures are available for drafting new documents. Templates are scoped to the authenticated entity: users via the web app or sk_ key see only their own templates;…
- [Delete a saved document template by ID.](https://docs.typebar.ai/api-reference/v1/delete-a-saved-document-template-by-id.md): Soft-deletes the template; only the owner (user or organization) can delete. Once deleted, the template no longer appears in list_user_templates and cannot be referenced by the AI for new documents. Existing documents already drafted from the template are unaffected.
- [Get Current User Profile](https://docs.typebar.ai/api-reference/users/get-current-user-profile.md): Get current user's profile information
- [Update User Profile](https://docs.typebar.ai/api-reference/users/update-user-profile.md): Update current user's profile
- [Get User Usage Stats](https://docs.typebar.ai/api-reference/users/get-user-usage-stats.md): Get detailed usage statistics for current user
- [Get User Sessions](https://docs.typebar.ai/api-reference/users/get-user-sessions.md): List all chat sessions for current user
- [Delete User Session](https://docs.typebar.ai/api-reference/users/delete-user-session.md): Delete a specific chat session
- [Check User Limits](https://docs.typebar.ai/api-reference/users/check-user-limits.md): Check current usage limits and remaining operations
- [List Api Keys](https://docs.typebar.ai/api-reference/users/list-api-keys.md): List all API keys for the current user (masked).
- [Create Api Key](https://docs.typebar.ai/api-reference/users/create-api-key.md): Create a new API key for the current user.
- [Revoke Api Key](https://docs.typebar.ai/api-reference/users/revoke-api-key.md): Revoke (soft delete) an API key.
- [Redeem Promo](https://docs.typebar.ai/api-reference/promo/redeem-promo.md): Redeem a promo code and add the granted operations to the authenticated user's account.
- [List My Promotions](https://docs.typebar.ai/api-reference/promo/list-my-promotions.md): List the authenticated user's promotion redemptions, split into `active` (drawable now) and `history` (exhausted / expired / revoked).
- [Get a pre-signed URL to upload large files (.docx/PDF/HTML/MD/RTF) without bloating agent context.](https://docs.typebar.ai/api-reference/uploads/get-a-pre-signed-url-to-upload-large-files-docxpdfhtmlmdrtf-without-bloating-agent-context.md): Returns a short-lived (5-minute) PUT URL plus a ready-to-run `curl_example`. An agent with shell access can run the `curl_example` directly to push the file to cloud storage, so the bytes never pass through its context window; clients without shell execution can surface the command or URL for the ca…
- [Parse an uploaded file into structured HTML with chunk IDs for targeted AI editing.](https://docs.typebar.ai/api-reference/uploads/parse-an-uploaded-file-into-structured-html-with-chunk-ids-for-targeted-ai-editing.md): Fetches the file uploaded via request_upload_url and runs the same parsing pipeline as upload_document_base64: every paragraph, heading, table, row, and cell gets a unique chunk ID, enabling targeted structural edits via chat ("remove row 3 of the pricing table" works), with tables, borders, shading…
- [Get a pre-signed URL to download an exported document without proxying through the agent.](https://docs.typebar.ai/api-reference/uploads/get-a-pre-signed-url-to-download-an-exported-document-without-proxying-through-the-agent.md): Returns a short-lived (15-minute) GET URL plus a ready-to-run `curl_example`. An agent with shell access can run the `curl_example` directly to save the exported file to the working directory, so the bytes never pass through its context window; clients without shell execution (or callers who only wa…
- [Agent Challenge](https://docs.typebar.ai/api-reference/agents/agent-challenge.md): Get a proof-of-work challenge for signup (only needed when the challenge gate is enabled).
- [Agent Signup](https://docs.typebar.ai/api-reference/agents/agent-signup.md): Create a SuperDocs account and get a working API key in one call — no human required.
- [Check your account status: subscription tier plus monthly operations used and remaining.](https://docs.typebar.ai/api-reference/agents/check-your-account-status:-subscription-tier-plus-monthly-operations-used-and-remaining.md): Check your SuperDocs account status: tier, monthly operations used/remaining, and (for agent accounts) whether a human has adopted it.
- [Agent Handoff](https://docs.typebar.ai/api-reference/agents/agent-handoff.md): Email your human a one-time link to ADOPT this account (take ownership + pay).
- [Agent Adopt](https://docs.typebar.ai/api-reference/agents/agent-adopt.md): Human takes over an agent account IN PLACE. Auth = the human's signed-in identity token.
- [Agent Adopt Info](https://docs.typebar.ai/api-reference/agents/agent-adopt-info.md): Public, token-keyed context for the adopt page: WHICH agent set this account up, where it runs, and where to find the takeover code. Recognition / anti-phishing only. NEVER returns the code itself; the unguessable token is the gate.
- [Agent Request Upgrade](https://docs.typebar.ai/api-reference/agents/agent-request-upgrade.md): For a FULLY AUTONOMOUS agent with no human who can upgrade: register interest in paying directly.
- [Root](https://docs.typebar.ai/api-reference/root.md)
- [Health Check Deep](https://docs.typebar.ai/api-reference/health-check-deep.md): Deep health check that verifies the job queue, AI workflow state store, and database are all responsive within a bounded time budget. Used by container orchestrators as a liveness probe to distinguish "process alive and TCP listening" (what /health reports) from "application is actually serving requ…
- [Oauth Protected Resource](https://docs.typebar.ai/api-reference/oauth-protected-resource.md)
- [Oauth Protected Resource](https://docs.typebar.ai/api-reference/oauth-protected-resource-1.md)
- [Oauth Protected Resource](https://docs.typebar.ai/api-reference/oauth-protected-resource-2.md)
- [Oauth Authorization Server](https://docs.typebar.ai/api-reference/oauth-authorization-server.md)
- [Oauth Authorization Server](https://docs.typebar.ai/api-reference/oauth-authorization-server-1.md)
- [Oauth Authorization Server](https://docs.typebar.ai/api-reference/oauth-authorization-server-2.md)
- [Openid Configuration](https://docs.typebar.ai/api-reference/openid-configuration.md)
- [Openid Configuration](https://docs.typebar.ai/api-reference/openid-configuration-1.md)
- [Openid Configuration](https://docs.typebar.ai/api-reference/openid-configuration-2.md)
- [Mcp Server Card](https://docs.typebar.ai/api-reference/mcp-server-card.md)
- [Mcp Server Card](https://docs.typebar.ai/api-reference/mcp-server-card-1.md)
- [Api Catalog](https://docs.typebar.ai/api-reference/api-catalog.md)
- [Verify the SuperDocs MCP server is reachable and serving traffic.](https://docs.typebar.ai/api-reference/mcp/verify-the-superdocs-mcp-server-is-reachable-and-serving-traffic.md): Returns 200 with {"status":"healthy"} when the API is up. Call this once after MCP install to confirm the connection works before invoking other tools. No authentication required.

## OpenAPI Specs

- [openapi](https://docs.typebar.ai/openapi.json)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.