什么是 Notion?
用于 Notion API 的 MCP 服务器,可搜索页面与数据库,并对页面、区块、评论和数据源进行 CRUD 管理。
核心功能 (25 个工具)
notion_searchSearch pages and databases in your Notion workspace by title. Filter by object type and sort by last edited time.
notion_create_pageCreate a new page in Notion. Set parent as a data source (data_source_id) or another page (page_id). Provide properties matching the parent schema. Optionally include initial content blocks.
notion_get_pageRetrieve a Notion page by ID. Returns properties, parent, timestamps, and URL. Use notion_get_block_children to read the page content.
notion_update_pageUpdate a Notion page. Change properties, icon, cover, or archive/trash status. Use block tools to update page content.
notion_move_pageMove a page to a new parent page or data source.
notion_get_page_propertyRetrieve a specific property value from a page. Useful for paginated properties like relations or rollups.
notion_get_blockRetrieve a single block by ID. Returns block type, content, and whether it has children.
notion_get_block_childrenGet child blocks of a page or block. This is how you read page content. Returns a paginated list of blocks.
notion_append_blocksAppend content blocks to a page or block. Max 100 blocks, 2 levels of nesting. Common types: paragraph, heading_1/2/3, bulleted_list_item, numbered_list_item, to_do, code, quote, callout, divider, table.
notion_update_blockUpdate a block's content. Send the block type key with updated data, e.g. { "paragraph": { "rich_text": [...] } }.
notion_delete_blockDelete (archive) a block. The block is moved to trash.
notion_create_data_sourceCreate a new data source (table) under an existing database. Data sources are individual tables within a database (API 2025-09-03).
notion_get_data_sourceRetrieve a data source by ID. Returns title, property schema, and timestamps.
notion_update_data_sourceUpdate a data source title or property schema.
notion_query_data_sourceQuery pages in a data source with filters and sorts. For new API (2025-09-03). For legacy databases use notion_query_database.
notion_list_data_source_templatesList page templates available in a data source.
notion_get_databaseGet a database by ID (legacy endpoint). Returns schema with properties and title. For new integrations prefer data source endpoints.
notion_query_databaseQuery a database with filters and sorts (legacy endpoint). For new integrations prefer notion_query_data_source.
notion_create_databaseCreate a new inline database inside a page (legacy). Must include at least one title property in the schema.
notion_create_commentCreate a comment on a page or reply in a discussion thread. Integration must have comment capabilities enabled.
notion_get_commentsList unresolved comments on a page or block.
notion_get_commentRetrieve a single comment by ID.
notion_list_usersList all users in the workspace. Returns names, types (person/bot), and avatars.
notion_get_userGet a user by ID.
notion_get_bot_userGet the bot user info for this integration. Useful for checking identity and permissions.
常见问题
Notion 是什么?
用于 Notion API 的 MCP 服务器,可搜索页面与数据库,并对页面、区块、评论和数据源进行 CRUD 管理。
Notion 提供哪些工具?
提供 25 个工具,包括 notion_search、notion_create_page、notion_get_page 等。
相关 Skills
表格处理
by anthropics
围绕 .xlsx、.xlsm、.csv、.tsv 做读写、修复、清洗、格式整理、公式计算与格式转换,适合修改现有表格、生成新报表或把杂乱数据整理成交付级电子表格。
✎ 做 Excel/CSV 相关任务很省心,能直接读写、修复、清洗和格式转换,尤其擅长把乱七八糟的表格整理成交付级文件。
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
Word文档
by anthropics
覆盖Word/.docx文档的创建、读取、编辑与重排,适合生成报告、备忘录、信函和模板,也能处理目录、页眉页脚、页码、图片替换、查找替换、修订批注及内容提取整理。
✎ 搞定 .docx 的创建、改写与精排版,目录、批量替换、批注修订和图片更新都能自动化,做正式文档尤其省心。
相关 MCP Server
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。
EdgarTools
编辑精选by dgunning
EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。
✎ 这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。