远程 MCP 服务器,可将 PDF 转为 Markdown、RAG 分块和带引用的表格,并发布可追踪的分享链接及阅读统计。
可以做什么
将 PDF 提取为干净的 Markdown 和结构化元素,可选仅正文的快速模式,或能重建表格与边界框的混合模式,返回规范的 ExtractedDocument 对象。把 PDF 切分为适合嵌入的语义分块,每块包含文本、估算 token 数、起始页、章节标题和用于引用的源元素 id。以结构化 JSON 列出 PDF 中的全部表格,附页码和边界框以便核验引用。将 PDF 发布为可追踪的 Doc Link 并获得可分享链接,可选设置过期时间和打开通知。列出账户下的 Doc Link,并读取每个链接的浏览量、独立访客和最近访问等统计。停用某个 Doc Link,使其公开地址停止提供内容。
适用场景
适合需要以 Markdown 阅读或引用 PDF 内容、为 RAG 流程准备 PDF,或从报告中提取表格并附带页码引用的场景。也适合把 PDF 作为可追踪链接分享并查看打开情况。
运行要求
使用 doc.page 上的远程 streamable HTTP 端点,无需本地运行时或安装包。免费匿名层无需凭据即可使用;可选的 Authorization 请求头携带 Bearer API 密钥以提高配额,Doc Link 相关工具必须提供。需要网络访问。
安装前请注意
Authorization 请求头携带密钥 API 密钥,请妥善保管。Doc Link 工具会把 PDF 发布为与该账户绑定的公开分享链接,停用后公开地址即停止提供内容。免费方案最多 3 个有效链接,自定义短链仅限付费方案。上传的 PDF 和链接统计由第三方服务处理。
Extract a PDF into clean Markdown and structured elements (headings, paragraphs). Returns the canonical ExtractedDocument object. mode "hybrid" runs a heavier semantic engine that also reconstructs tables and bounding boxes; the default "fast" engine is prose-only (low confidence.tables).
输入参数url必填modeoutputschunkTokens
get_chunks
Split a PDF into semantic chunks ready for embeddings (RAG). Each chunk carries its text, estimated tokens, starting page, section heading and the source element ids for citation.
输入参数url必填maxTokens
list_tables
Return every table in a PDF as structured JSON (reconstructed rows and columns) with page and bounding box for verifiable citations. Uses the semantic (hybrid) engine.
输入参数url必填
create_doc_link
Publish a PDF as a tracked doc.page Doc Link and get back a shareable URL. The link belongs to the API key's account and also appears in its doc.page library. Requires an API key. Free plan: up to 3 active links; custom vanity slugs are premium-only. Optional expiry and open-notification toggle.
输入参数url必填nameslugexpiresAtnotifyOnOpen
list_doc_links
List the Doc Links of the API key's account (id, slug, URL, name, disabled/expiry state, total views, last view). Use this to recover links created in earlier sessions before querying stats. Requires an API key.
无需输入参数。
get_doc_link_stats
Reading analytics for one Doc Link of the API key's account, by id or slug. Always returns the summary (total views, unique visitors, last visit). Premium plans additionally get countries, visitor companies (as_org) and per-page views + average dwell time; pass include:["visits"] for the recent visit rows. Requires an API key.
输入参数idsluginclude
revoke_doc_link
Disable a Doc Link of the API key's account (by id or slug) so the public URL stops serving. The item and its stats remain in the library; on the free plan this frees an active-link slot. Requires an API key.