doc.page PDF Extraction is an MCP server with 7 tools an agent can call, among them create_doc_link, extract_pdf, get_chunks. It answers at https://doc.page/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 pre Inputs: url, name, slug, expiresAt, notifyOnOpen |
extract_pdf | 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 "fa Inputs: url, outputs, mode, chunkTokens |
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. Inputs: url, maxTokens |
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 + ave Inputs: id, slug, include |
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. |
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. Inputs: url |
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. Inputs: id, slug |
Every block below points at https://doc.page/api/mcp. Pick your client and copy.
claude mcp add --transport http doc-page-pdf-extraction https://doc.page/api/mcp
{
"mcpServers": {
"doc-page-pdf-extraction": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://doc.page/api/mcp"]
}
}
}{
"mcpServers": {
"doc-page-pdf-extraction": {
"url": "https://doc.page/api/mcp"
}
}
}{
"servers": {
"doc-page-pdf-extraction": {
"type": "http",
"url": "https://doc.page/api/mcp"
}
}
}{
"context_servers": {
"doc-page-pdf-extraction": {
"url": "https://doc.page/api/mcp"
}
}
}{
"mcpServers": {
"doc-page-pdf-extraction": {
"serverUrl": "https://doc.page/api/mcp"
}
}
}{
"mcpServers": {
"doc-page-pdf-extraction": {
"url": "https://doc.page/api/mcp"
}
}
}name: doc.page PDF Extraction
version: 0.0.1
schema: v1
mcpServers:
- name: doc.page PDF Extraction
type: streamable-http
url: https://doc.page/api/mcp{
"mcpServers": {
"doc-page-pdf-extraction": {
"httpUrl": "https://doc.page/api/mcp"
}
}
}{
"mcpServers": {
"doc-page-pdf-extraction": {
"type": "http",
"url": "https://doc.page/api/mcp"
}
}
}{
"mcpServers": {
"doc-page-pdf-extraction": {
"url": "https://doc.page/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fdoc.page%2Fapi%2Fmcp&type=streamable_http&id=doc-page-pdf-extraction&name=doc.page%20PDF%20Extraction
It answered our last check on 24 October 2026 in 412 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by doc.page and served from doc.page, the vendor's own domain: https://doc.page/api/mcp.
7, as returned by the server's own tools/list on 23 September 2026: create_doc_link, extract_pdf, get_chunks, get_doc_link_stats, list_doc_links, list_tables, revoke_doc_link.
It answered our last check on 24 October 2026 in 412 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://doc.page/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: page.doc. Endpoint host: doc.page. ARD identifier: urn:air:page.doc:mcp:pdf-extract.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.