This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · closeread.cn
21tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://closeread.cn/mcp
Skill page: https://www.mcpbundles.com/skills/closeread-mcp-55d2a49b6d
Generate Doc — Generate a bilingual close-reading document from English text or an SRT subtitle.
Submits an async job and returns immediately with a task_id; poll get_doc until
status is "SUCCESS" (statuses are uppercase: PENDING / PROCESSING / SUCCESS /
FAILED). Personalization (vocabulary level / Zipf threshold) always follows the
key owner's profile and cannot be overridden here.
Args:
source_type: "text" (pasted English text) or "srt" (SRT subtitle file content).
text:
Upload Audio — Attach a full-length audio track (by public URL) to make a spoken document.
The server fetches the audio from the URL, validates size/duration, stores it,
and marks the document as a spoken (uploaded-audio) version. SRT-sourced
documents only. Idempotent: if audio already exists, returns current status.
Args:
task_id: The document task_id (must belong to the key owner).
audio_url: A public http(s) direct link to the audio file (mp3/m4a/aac/wav).
Returns:
Set Title Summary — Edit a document's title and/or English/Chinese summary (author only).
Each field is optional: omit (null) to leave unchanged; empty string clears the
summary fields (title cannot be cleared).
Args:
task_id: The document task_id (must belong to the key owner).
title: New title (optional).
summary_en: New English summary, or "" to clear (optional).
summary_zh: New Chinese summary, or "" to clear (optional).
Returns:
{ok: true} on success,
List My Docs — List documents created by the authenticated account (newest first).
Only the key owner's own documents (not forks). Use this to find task_ids and
doc URLs to share. Page through all docs with `offset`: keep increasing it by
`limit` until you get fewer than `limit` items (that's the last page).
Args:
limit: Max items per page (default 50, 1–200).
offset: Skip the first N items (pagination; 0 = first page).
since: ISO-8601 timestamp; only return documents
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does 文稿生 provide?
Operate this server?
Request removal if you do not want 文稿生 listed here, or claim the listing if you want to manage it on MCPBundles.
Operate 文稿生?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Get Doc — Get status and metadata for one of your documents.
Poll this after generate_doc until `status` is "SUCCESS" (uppercase: PENDING /
PROCESSING / SUCCESS / FAILED). For spoken documents it also returns the
audio_url once available.
Args:
task_id: The document task_id (must belong to the key owner).
Returns:
{status, title, doc_url, visibility, error?, audio_url?}, or a structured
error dict on auth failure.
Get Doc Content — Get the full annotated content (result_json) of one of your documents.
Returns the bilingual sentences, vocabulary annotations, levels, title and
summaries — everything needed to render or post-process the doc downstream.
Author only.
Args:
task_id: The document task_id (must belong to the key owner).
Returns:
{task_id, title, summary_en, summary_zh, visibility, source_lang, gloss_lang,
result} where `result` is the full result_json, or a structured
Get Quota Status — Get the account's token quota / rolling-window status, tier and word limit.
Use before generating to know remaining budget, and to explain limits to the user.
Returns:
{tier, word_limit (null = unlimited), windows: {session?/weekly?/monthly: {used,
limit, pct, reset_in_seconds, status}}}, or a structured error dict.
Get Vocab Profile — Get the account's personalization profile used for annotation.
Generation always annotates against this profile (vocab size / Zipf threshold /
levels / pronunciation accent) — read it to understand how docs will be marked.
Returns:
{vocab_size, zipf_threshold, vocab_levels, pron_accent}, or a structured error dict.
List My Groups — List the learning groups (学习圈, R28) you own or have joined.
Returns:
{owned: [{group_id, name}], joined: [{group_id, name}]}, or a structured error dict.
Reannotate Doc — Re-annotate one of your documents against new exam levels / your vocab threshold.
Reuses existing translations (no re-translation, no LLM cost beyond annotation),
overwrites the current doc. Async — poll get_doc until status SUCCESS. Author only.
Args:
task_id: The document task_id (must belong to the key owner).
levels: Exam vocab levels to annotate against (e.g. ["cet4","cet6"]). Omit
to fall back to the key owner's global `vocab_levels` profile (then
Edit Doc Sentence — Edit one sentence's English original and/or Chinese translation (R13, owner only).
Editing `en` re-annotates that sentence (no LLM) and re-renders the PDF; editing `zh`
just updates the text. Audio (if any) may become inconsistent with the new text.
Args:
task_id: The document task_id (must belong to the key owner).
index: 0-based sentence index.
en: New English text (optional).
zh: New Chinese translation (optional). Provide at least one of en/zh.
Set Vocab Prefs — Update your annotation preferences (affects how FUTURE docs are annotated).
Args:
levels: Exam levels / wordlists to prefer (empty list = unset). Replaces the
current set.
pron_accent: "us" or "uk" (omit to leave unchanged).
Returns:
{vocab_levels, pron_accent} on success, or a structured error dict.
Download Pdf — Get the PDF download URL and generation status for your document.
The URL needs your API key (Bearer) to fetch. If status isn't "done" yet, the PDF is
still rendering. Author only.
Args:
task_id: The document task_id (must belong to the key owner).
Returns:
{pdf_status, download_url}, or a structured error dict.
Set Visibility — Change a document's visibility. Owner only.
⚠️ DANGER: setting a private doc to "public"/"unlisted" exposes it publicly.
**You MUST pass confirm=true** to proceed — read the change aloud to the user first.
Args:
task_id: The document task_id (must belong to the key owner).
visibility: One of "private" / "unlisted" / "restricted" / "public" / "group_visible".
confirm: Must be true to apply (safety gate against accidental exposure).
emails: For "restri
Set Enable Fork — Toggle whether others can derive a personalized child ("跟学") from your doc.
Args:
task_id: The document task_id (must belong to the key owner).
enable: True to allow forking, False to disallow.
Returns:
{ok: true, enable_fork} on success, or a structured error dict.
Create Child — Derive your own personalized child copy ("跟学") of a forkable document.
Idempotent: if you already have a child of this parent, returns it (no extra cost).
First create costs tokens. The parent must allow forking and be visible to you.
Args:
parent_task_id: The parent document's task_id.
Returns:
{ok: true, child_task_id, ...} on success, or a structured error dict.
Like Doc — Like a document you can view (R12).
Args:
task_id: The document task_id.
Returns:
The like result, or a structured error dict.
Follow User — Follow a user by their @username (R12).
Args:
username: The target user's unique @username (without the @).
Returns:
The follow result, or a structured error dict.
Share Poster — Get the share-poster image URL for your document (server-rendered PNG).
The poster is gated by the doc's visibility (private docs can't be shared). The URL
renders/returns the poster on fetch. Author only here.
Args:
task_id: The document task_id (must belong to the key owner).
include_qr: Optional QR toggle. None = visibility default (public/paid carry a
QR that links back to the doc, unlisted/guest-public don't). Set False to
drop the QR (e
Delete Doc — Permanently delete ONE of your documents. **IRREVERSIBLE.**
Cascades to the document's audio, poster and PDF, and leaves a tombstone for anyone
who forked it ("原作者已删除"). Author only.
Safety protocol: call once WITHOUT confirm to get the title, **read it to the user for
explicit confirmation**, then call again with confirm=true. One document per call —
never batch deletes.
Args:
task_id: The document task_id (must belong to the key owner).
confirm: Must
MCPBundles probed 21 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does 文稿生 require?
文稿生 may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.