Readwise MCP

Use the Readwise MCP tools to access the user's Readwise highlights and Reader documents. Readwise has two products:

Readwise — highlights from books, articles, podcasts, and more. Includes daily review and spaced repetition.
Reader — a read-later app for saving and reading articles, PDFs, EPUBs, RSS feeds, emails, tweets, and videos.

使用Readwise MCP工具访问用户的Readwise高亮内容和Reader文档。Readwise有两款产品：

Readwise —— 来自书籍、文章、播客等内容的高亮标记。包含每日复习和间隔重复功能。
Reader —— 一款稍后阅读应用，用于保存和阅读文章、PDF、EPUB、RSS订阅源、邮件、推文和视频。

Setup

设置

Add the Readwise MCP server to your client's configuration:

json

{
  "readwise": {
    "type": "http",
    "url": "https://mcp2.readwise.io/mcp"
  }
}

The server handles authentication via OAuth — the user will be prompted to authorize on first use.

将Readwise MCP服务器添加到客户端配置中：

json

{
  "readwise": {
    "type": "http",
    "url": "https://mcp2.readwise.io/mcp"
  }
}

服务器通过OAuth处理身份验证——用户首次使用时会被提示进行授权。

Tool Reference

工具参考

All tools are prefixed with

mcp__readwise__

. Each tool name maps directly to a Readwise or Reader API action.

所有工具均以

mcp__readwise__

为前缀。每个工具名称直接对应Readwise或Reader的API操作。

Reader Tools

Reader工具

Searching documents

搜索文档

reader_search_documents(query="spaced repetition")

Hybrid search (semantic + keyword) across all saved documents. Combine with filters to narrow results:

undefined

reader_search_documents(query="spaced repetition")

混合搜索（语义+关键词）覆盖所有已保存文档。结合筛选器缩小结果范围：

undefined

Search articles saved for later

搜索稍后保存的文章

reader_search_documents(query="machine learning", category_in=["article"], location_in=["later", "shortlist"])

Search by author

按作者搜索

reader_search_documents(query="AI agents", author_search="Simon Willison")

Search within a date range

按日期范围搜索

reader_search_documents(query="transformers", published_date_gt="2024-01-01")

Search by tags

按标签搜索

reader_search_documents(query="productivity", tags_in=["research"])


Other filters: `title_search`, `summary_search`, `note_search`, `url_search`, `source_search`, `document_id`, `limit` (default 20, max 100).

reader_search_documents(query="productivity", tags_in=["research"])


其他筛选器：`title_search`、`summary_search`、`note_search`、`url_search`、`source_search`、`document_id`、`limit`（默认20，最大100）。

Browsing documents

浏览文档

undefined

undefined

List 10 most recent inbox items with minimal fields

列出10条最新收件箱项目，仅返回必要字段

reader_list_documents(location="new", limit=10, response_fields=["title", "author", "summary", "word_count", "category", "saved_at"])

Archived articles with a specific tag

带有特定标签的已归档文章

reader_list_documents(location="archive", tag=["research"], category="article")

Unseen inbox items

未读收件箱项目

reader_list_documents(location="new", seen=false)

RSS feed items

RSS订阅源项目

reader_list_documents(location="feed", limit=20, response_fields=["title", "author", "summary", "site_name"])

Get a specific document by ID

通过ID获取特定文档

reader_list_documents(id="<document_id>")

Paginate through results

分页查看结果

reader_list_documents(location="later", limit=10, page_cursor="<cursor_from_previous_response>")


Locations: `new` (inbox), `later`, `shortlist`, `archive`, `feed`. When the user says "inbox", use `new`. Only use `feed` when the user explicitly asks about RSS/feeds.

Use `response_fields` to limit returned data and save tokens. The `id` field is always included. Available fields: `url`, `title`, `author`, `source`, `category`, `location`, `tags`, `site_name`, `word_count`, `reading_time`, `created_at`, `updated_at`, `published_date`, `summary`, `image_url`, `content`, `source_url`, `notes`, `parent_id`, `reading_progress`, `first_opened_at`, `last_opened_at`, `saved_at`, `last_moved_at`, `html_content`, `is_deleted`.

Tip: unseen documents have `first_opened_at=null`. Mark as seen via `reader_bulk_edit_document_metadata`.

reader_list_documents(location="later", limit=10, page_cursor="<cursor_from_previous_response>")


位置选项：`new`（收件箱）、`later`、`shortlist`、`archive`、`feed`。当用户提到“收件箱”时，使用`new`。仅当用户明确询问RSS/订阅源时才使用`feed`。

使用`response_fields`限制返回数据以节省token。`id`字段始终会被包含。可用字段包括：`url`、`title`、`author`、`source`、`category`、`location`、`tags`、`site_name`、`word_count`、`reading_time`、`created_at`、`updated_at`、`published_date`、`summary`、`image_url`、`content`、`source_url`、`notes`、`parent_id`、`reading_progress`、`first_opened_at`、`last_opened_at`、`saved_at`、`last_moved_at`、`html_content`、`is_deleted`。

提示：未读文档的`first_opened_at`为`null`。可通过`reader_bulk_edit_document_metadata`标记为已读。

Reading and highlighting

阅读与高亮标记

undefined

undefined

Get full document details including Markdown content

获取完整文档详情，包括Markdown内容

reader_get_document_details(document_id="<id>")

Get all highlights on a document

获取某文档的所有高亮标记

reader_get_document_highlights(document_id="<id>")

Create a highlight — html_content must match the document's HTML exactly

创建高亮标记——html_content必须与文档的HTML完全匹配

Get the HTML via reader_list_documents with response_fields=["html_content"]

通过reader_list_documents并指定response_fields=["html_content"]获取HTML

reader_create_highlight(document_id="<id>", html_content="The exact passage to highlight")

Highlight with a note and tags

创建带备注和标签的高亮标记

reader_create_highlight(document_id="<id>", html_content="Key insight", note="Connects to spaced repetition", tags=["review", "concept"])

undefined

reader_create_highlight(document_id="<id>", html_content="Key insight", note="Connects to spaced repetition", tags=["review", "concept"])

undefined

Saving documents

保存文档

undefined

undefined

Save a URL — Reader scrapes it automatically

保存一个URL——Reader会自动抓取内容

reader_create_document(url="https://example.com/article")

Save with metadata and tags

保存时添加元数据和标签

reader_create_document(url="https://example.com", title="Great Article", tags=["research", "ai"], notes="Recommended by Alice")

Save raw Markdown content (provide a unique URL as identifier)

保存原始Markdown内容（需提供唯一URL作为标识符）

reader_create_document(title="Meeting Notes", markdown="# Notes from today...", url="https://me.com#notes-march-2025")

undefined

reader_create_document(title="Meeting Notes", markdown="# Notes from today...", url="https://me.com#notes-march-2025")

undefined

Organizing

整理文档

undefined

undefined

Move documents between locations (max 50 per call)

在不同位置间移动文档（每次调用最多50个）

reader_move_documents(document_ids=["<id1>", "<id2>"], location="archive")

Bulk mark documents as seen

批量标记文档为已读

reader_bulk_edit_document_metadata(documents=[{"document_id": "<id>", "seen": true}])

Bulk update metadata

批量更新元数据

reader_bulk_edit_document_metadata(documents=[{"document_id": "<id>", "title": "Better Title", "tags": ["ai", "research"]}])


Note: `reader_move_documents` and `reader_bulk_edit_document_metadata` share a rate limit of 20 calls/minute. Batch document IDs into fewer calls.

reader_bulk_edit_document_metadata(documents=[{"document_id": "<id>", "title": "Better Title", "tags": ["ai", "research"]}])


注意：`reader_move_documents`和`reader_bulk_edit_document_metadata`共享每分钟20次调用的速率限制。请将文档ID分批以减少调用次数。

标签管理

undefined

undefined

List all tags

列出所有标签

reader_list_tags()

Add tags to a document

为文档添加标签

reader_add_tags_to_document(document_id="<id>", tag_names=["important", "research"])

Remove tags from a document

移除文档的标签

reader_remove_tags_from_document(document_id="<id>", tag_names=["old-tag"])

Add tags to a highlight

为高亮标记添加标签

reader_add_tags_to_highlight(document_id="<id>", highlight_document_id="<hid>", tag_names=["concept"])

Remove tags from a highlight

移除高亮标记的标签

reader_remove_tags_from_highlight(document_id="<id>", highlight_document_id="<hid>", tag_names=["old-tag"])

Set notes on a highlight (pass null to clear)

设置高亮标记的备注（传入null可清除）

reader_set_highlight_notes(document_id="<id>", highlight_document_id="<hid>", notes="My updated note")

undefined

reader_set_highlight_notes(document_id="<id>", highlight_document_id="<hid>", notes="My updated note")

undefined

Exporting

导出文档

undefined

undefined

Export all documents as a ZIP of Markdown files (async — returns export_id)

将所有文档导出为Markdown文件的ZIP包（异步操作——返回export_id）

reader_export_documents()

Delta export — only docs updated since last export

增量导出——仅导出上次导出后更新的文档

reader_export_documents(since_updated="2024-01-01T00:00:00Z")

Poll for completion

查询导出完成状态

reader_get_export_documents_status(export_id="<id>")


Poll `reader_get_export_documents_status` until `status` is `"completed"`, then use the `download_url`.

reader_get_export_documents_status(export_id="<id>")


轮询`reader_get_export_documents_status`直到`status`变为`"completed"`，然后使用返回的`download_url`下载。

Readwise Tools

Readwise工具

Searching highlights

搜索高亮标记

undefined

undefined

Semantic search across all highlights

对所有高亮标记进行语义搜索

readwise_search_highlights(vector_search_term="learning techniques")

Search with full-text filter on a specific field

结合特定字段的全文搜索筛选

readwise_search_highlights(vector_search_term="memory", full_text_queries=[{"field_name": "document_title", "search_term": "psychology"}])


Full-text query fields: `document_author`, `document_title`, `highlight_note`, `highlight_plaintext`, `highlight_tags`.

readwise_search_highlights(vector_search_term="memory", full_text_queries=[{"field_name": "document_title", "search_term": "psychology"}])


全文查询支持的字段：`document_author`、`document_title`、`highlight_note`、`highlight_plaintext`、`highlight_tags`。

Browsing highlights

浏览高亮标记

undefined

undefined

List 20 most recent highlights

列出20条最新的高亮标记

readwise_list_highlights(page_size=20)

Highlights from a specific book

某本书的高亮标记

readwise_list_highlights(book_id=12345)

Highlights from the last month

近一个月的高亮标记

readwise_list_highlights(highlighted_at_gt="2025-02-01T00:00:00Z")

Paginate

分页查看

readwise_list_highlights(page_size=100, page=2)

undefined

readwise_list_highlights(page_size=100, page=2)

undefined

Creating and editing highlights

创建与编辑高亮标记

undefined

undefined

Create a highlight (matched to a book by title/author, or goes into "Quotes")

创建高亮标记（通过标题/作者匹配书籍，否则归入“引用”分类）

readwise_create_highlights(highlights=[{"text": "The key insight here", "title": "Book Title", "author": "Author Name"}])

Create multiple highlights at once

批量创建多个高亮标记

readwise_create_highlights(highlights=[{"text": "First quote", "title": "Book A"}, {"text": "Second quote", "title": "Book B", "note": "Great point"}])

Update a highlight

更新高亮标记

readwise_update_highlight(highlight_id=12345, note="New note", add_tags=["concept", "review"], color="blue")

Delete a highlight

删除高亮标记

readwise_delete_highlight(highlight_id=12345)


Colors: `yellow`, `blue`, `pink`, `orange`, `green`, `purple`.

readwise_delete_highlight(highlight_id=12345)


颜色选项：`yellow`、`blue`、`pink`、`orange`、`green`、`purple`。

Daily review

每日复习

undefined

undefined

Get today's spaced repetition review

获取今日的间隔重复复习内容

readwise_get_daily_review()


Returns highlights selected by the algorithm plus a URL for interactive review.

readwise_get_daily_review()


返回算法筛选的高亮标记，以及一个用于交互式复习的URL。

Example Workflows

示例工作流

Triage the inbox: List recent saves, read each one, decide what's worth the user's time.

reader_list_documents(location="new", limit=10, response_fields=["title", "author", "summary", "word_count", "category", "saved_at"])
reader_get_document_details(document_id="<id>")
reader_move_documents(document_ids=["<id>"], location="later")     # worth reading
reader_move_documents(document_ids=["<id>"], location="archive")   # skip

Search across everything: Find all content on a topic — run both in parallel.

reader_search_documents(query="spaced repetition")
readwise_search_highlights(vector_search_term="spaced repetition")

Quiz on a recent read: Find a finished document, get its content and highlights.

reader_list_documents(location="archive", limit=10, response_fields=["title", "author", "summary", "word_count"])
reader_get_document_details(document_id="<id>")
reader_get_document_highlights(document_id="<id>")

Catch up on RSS: Browse feed items, surface the best ones, mark the rest as seen.

reader_list_documents(location="feed", limit=20, response_fields=["title", "author", "summary", "word_count", "site_name"])
reader_bulk_edit_document_metadata(documents=[{"document_id": "<id1>", "seen": true}, {"document_id": "<id2>", "seen": true}])
reader_move_documents(document_ids=["<id>"], location="later")

Save and annotate: Save a URL, highlight key passages, tag and organize.

reader_create_document(url="https://example.com/article", tags=["research"])
reader_create_highlight(document_id="<id>", html_content="<p>Key passage here</p>", note="This connects to...")
reader_add_tags_to_document(document_id="<id>", tag_names=["important"])

Build a reading recap: See what you've finished and highlighted recently.

reader_list_documents(location="archive", updated_after="2025-03-10T00:00:00Z", response_fields=["title", "author", "word_count", "reading_progress"])
reader_get_document_highlights(document_id="<id>")
readwise_list_highlights(highlighted_at_gt="2025-03-10T00:00:00Z", page_size=50)

**收件箱分类：**列出最近保存的内容，逐一查看，判断是否值得用户花费时间。

reader_list_documents(location="new", limit=10, response_fields=["title", "author", "summary", "word_count", "category", "saved_at"])
reader_get_document_details(document_id="<id>")
reader_move_documents(document_ids=["<id>"], location="later")     # 值得阅读
reader_move_documents(document_ids=["<id>"], location="archive")   # 跳过

**全内容搜索：**查找某主题的所有内容——并行运行以下两个操作。

reader_search_documents(query="spaced repetition")
readwise_search_highlights(vector_search_term="spaced repetition")

**近期阅读测验：**找到已读完的文档，获取其内容和高亮标记。

reader_list_documents(location="archive", limit=10, response_fields=["title", "author", "summary", "word_count"])
reader_get_document_details(document_id="<id>")
reader_get_document_highlights(document_id="<id>")

**跟进RSS内容：**浏览订阅源项目，筛选优质内容，标记其余为已读。

reader_list_documents(location="feed", limit=20, response_fields=["title", "author", "summary", "word_count", "site_name"])
reader_bulk_edit_document_metadata(documents=[{"document_id": "<id1>", "seen": true}, {"document_id": "<id2>", "seen": true}])
reader_move_documents(document_ids=["<id>"], location="later")

**保存与批注：**保存URL，高亮关键段落，添加标签并整理。

reader_create_document(url="https://example.com/article", tags=["research"])
reader_create_highlight(document_id="<id>", html_content="<p>Key passage here</p>", note="This connects to...")
reader_add_tags_to_document(document_id="<id>", tag_names=["important"])

**生成阅读回顾：**查看近期已完成的阅读和高亮标记。

reader_list_documents(location="archive", updated_after="2025-03-10T00:00:00Z", response_fields=["title", "author", "word_count", "reading_progress"])
reader_get_document_highlights(document_id="<id>")
readwise_list_highlights(highlighted_at_gt="2025-03-10T00:00:00Z", page_size=50)

readwise-mcp

Original

Translation

Readwise MCP

Readwise MCP

Setup

设置

Tool Reference

工具参考

Reader Tools

Reader工具

Searching documents

搜索文档

Search articles saved for later

搜索稍后保存的文章

Search by author

按作者搜索

Search within a date range

按日期范围搜索

Search by tags

按标签搜索

Browsing documents

浏览文档

List 10 most recent inbox items with minimal fields

列出10条最新收件箱项目，仅返回必要字段

Archived articles with a specific tag

带有特定标签的已归档文章

Unseen inbox items

未读收件箱项目

RSS feed items

RSS订阅源项目

Get a specific document by ID

通过ID获取特定文档

Paginate through results

分页查看结果

Reading and highlighting

阅读与高亮标记

Get full document details including Markdown content

获取完整文档详情，包括Markdown内容

Get all highlights on a document

获取某文档的所有高亮标记

Create a highlight — html_content must match the document's HTML exactly

创建高亮标记——html_content必须与文档的HTML完全匹配

Get the HTML via reader_list_documents with response_fields=["html_content"]

通过reader_list_documents并指定response_fields=["html_content"]获取HTML

Highlight with a note and tags

创建带备注和标签的高亮标记

Saving documents

保存文档

Save a URL — Reader scrapes it automatically

保存一个URL——Reader会自动抓取内容

Save with metadata and tags

保存时添加元数据和标签

Save raw Markdown content (provide a unique URL as identifier)

保存原始Markdown内容（需提供唯一URL作为标识符）

Organizing

整理文档

Move documents between locations (max 50 per call)

在不同位置间移动文档（每次调用最多50个）

Bulk mark documents as seen

批量标记文档为已读

Bulk update metadata

批量更新元数据

Tags

标签管理

List all tags

列出所有标签

Add tags to a document

为文档添加标签

Remove tags from a document

移除文档的标签

Add tags to a highlight

为高亮标记添加标签

Remove tags from a highlight

移除高亮标记的标签

Set notes on a highlight (pass null to clear)

设置高亮标记的备注（传入null可清除）

Exporting

导出文档

Export all documents as a ZIP of Markdown files (async — returns export_id)