Skip to content

doc.page PDF Extraction MCP server

page.doc/pdf-extractdoc.pagestreamable-httpv1.1.0Scanned

Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.

7 tools: 1 can delete or cancel things, 1 do something that can't be undone, 1 change things and 4 only read.

Tools: 1 delete, 1 irreversible, 1 write, 4 read.
  • Reads private data · 3
  • Reads text others write · 3
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the doc.page PDF Extraction MCP server can do

The doc.page PDF Extraction MCP server is published by doc.page, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (1 tool: revoke_doc_link), do things that cannot be undone, such as sending, paying or publishing (create_doc_link) and create or change data (1 tool: extract_pdf). 4 tools only read.

3 tools read private data (list_tables, list_doc_links and get_doc_link_stats); 3 tools bring in text other people can write (get_chunks, list_tables and list_doc_links); 4 tools can send data out of your system (extract_pdf, get_chunks, list_tables and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 1.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Deletes or cancels 1Claude Code: deny
Can't be undone 1Claude Code: ask
Changes things 1Claude Code: ask
  • extract_pdfExtract a PDF into clean Markdown and structured elements (headings, paragraphs).Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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).
Only reads 4Show 4 read-only tools
  • get_chunksSplit a PDF into semantic chunks ready for embeddings (RAG).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_chunks" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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.
  • list_tablesReturn every table in a PDF as structured JSON (reconstructed rows and columns) with page and bounding box for verifiable citations.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "list_tables" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_tables" says "list" and "table": it reads databases.
    • private-dataThe description's first sentence says "return" and "table": it reads databases.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

36 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 untrusted-input tools breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__pdf-extract__get_chunks",
      "mcp__pdf-extract__list_doc_links",
      "mcp__pdf-extract__list_tables"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:17 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 destructive, 1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://doc.page/api/mcp: tools/list returned 7 tools to an anonymous client, including revoke_doc_link (destructive), create_doc_link (irreversible), extract_pdf (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http pdf-extract https://doc.page/api/mcp
claude mcp add --transport http pdf-extract https://doc.page/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__pdf-extract__list_doc_links",
      "mcp__pdf-extract__get_doc_link_stats"
    ],
    "ask": [
      "mcp__pdf-extract__extract_pdf",
      "mcp__pdf-extract__get_chunks",
      "mcp__pdf-extract__list_tables",
      "mcp__pdf-extract__create_doc_link"
    ],
    "deny": [
      "mcp__pdf-extract__revoke_doc_link"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as pdf-extract. Review it before you use it.

Capability tags behind 6 rules
  • mcp__pdf-extract__extract_pdf outbound
  • mcp__pdf-extract__get_chunks untrusted-input, outbound
  • mcp__pdf-extract__list_tables private-data, untrusted-input, outbound
  • mcp__pdf-extract__create_doc_link outbound
  • mcp__pdf-extract__list_doc_links private-data, untrusted-input
  • mcp__pdf-extract__get_doc_link_stats private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/page.doc/pdf-extract/verify?hash=f8d152b4c57e0940e5039ceb9427da3c2d7745077c9c2f2f7f3d01882954c2ae" | jq -e '.changed == false'

Pinned hash f8d152b4c57e, from Nov 19, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/page.doc/pdf-extract/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for page.doc/pdf-extract
[![Anlyon Radar](https://radar.anlyon.com/badge/page.doc/pdf-extract.svg)](https://radar.anlyon.com/servers/page.doc/pdf-extract)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

doc.page PDF Extraction MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the doc.page PDF Extraction MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the doc.page PDF Extraction MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: revoke_doc_link.

Can the doc.page PDF Extraction MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: create_doc_link.

What tools does the doc.page PDF Extraction MCP server have?

7 tools: 1 destructive, 1 irreversible, 1 write, 4 read. revoke_doc_link, create_doc_link, extract_pdf, get_chunks, list_tables, list_doc_links and get_doc_link_stats.

Does the doc.page PDF Extraction MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the doc.page PDF Extraction MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract_pdf, get_chunks, list_tables and create_doc_link.

Has the doc.page PDF Extraction MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.