🔌

doc.page PDF ExtractionPublisher🛡 No advisories

page.doc/pdf-extract

New to MCP? Start here →

0★ stars

0weekly installs

11 days agolast release

Provenancewhere it came from, and what was verified

✦

First-party publisher

Published by the owner of doc.page, who proved control of the domain through the official MCP registry.

Verified owner: doc.page ↗page.doc/pdf-extract

🛡 Permissions & trustwhat this server can touch before you run it

◆

Network access

Connects to a hosted remote endpoint.

About

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

Packages & transports

remotehttps://doc.page/api/mcpHTTP

Metadata

Quality 78/100

how much you can lean on this server

Maintenance

45/45

Completeness

22/35

Reliability

11/20

Computed from the server's own data, not a hidden formula. This measures how much you can depend on it, not how popular it is. Stars are shown separately, on purpose. How it's scored →

Tool definition quality 96/100

how well its 7 tools describe themselves to an agent

▸extract_pdf100A

Description

present and substantive

Param types

params declare a type

Param docs

params are described

Structure

required fields declared

▸get_chunks100A

Description

present and substantive

Param types

params declare a type

Param docs

params are described

Structure

required fields declared

▸list_tables100A

Description

present and substantive

Param types

params declare a type

Param docs

params are described

Structure

required fields declared

▸create_doc_link100A

Description

present and substantive

Param types

params declare a type

Param docs

params are described

Structure

required fields declared

▸list_doc_links100A

Description

present and substantive

Param types

no parameters

Param docs

no parameters

Structure

required fields declared

▸get_doc_link_stats93A

Description

present and substantive

Param types

params declare a type

Param docs

params are described

Structure

required fields declared

▸revoke_doc_link93A

Description

present and substantive

Param types

params declare a type

Param docs

params are described

Structure

required fields declared

Structural, not an LLM's opinion: each check is a fact about the tool's schema, so it's reproducible. One weak tool drags the score (60% average, 40% worst). How it's scored →

For the maintainer

Raise this grade

up to +22 on quality

Own this server? Here's exactly what to change, biggest wins first. Every number below is a fixed point value, so you can see what each edit is worth before you make it.

Collect working reviewsReliability

With no reviews this sits at a neutral 11. Reviews reporting it works push it toward the full 20.

Declare a licenseCompleteness

Add an SPDX license (like MIT or Apache-2.0) to the repo so it's detected.

Link the sourceCompleteness

Add a public source repository URL.

Tool definitions to fix first

get_doc_link_stats93/100

No `required` array. Declare which params are mandatory so an agent knows what it must provide.

revoke_doc_link93/100

No `required` array. Declare which params are mandatory so an agent knows what it must provide.

Already earned (3) ▾

✓Describe what it does+11

✓Give an install path+11

✓Keep it active+45

These are structural checks, so the fixes are exact. See the full formula →

Add a badge to your README

[![SocketCat](https://socketcat.com/badge/page.doc/pdf-extract)](https://socketcat.com/servers/page.doc/pdf-extract)

Shows your live quality grade and links back here. It updates itself as the grade changes.

Add to your client

Pick your client, copy, paste into its config. That's the whole setup.

~/.claude/claude_desktop_config.json

{
  "mcpServers": {
    "pdf_extract": {
      "command": "npx",
      "args": [
        "-y",
        "pdf-extract"
      ]
    }
  }
}

▶ Try itlive against doc.page

This server has a hosted endpoint, so we can connect and list its actual tools right here. Nothing runs on your machine.

doc.page PDF Extraction✦Publisher🛡 No advisories

Provenancewhere it came from, and what was verified

🛡 Permissions & trustwhat this server can touch before you run it

About

Packages & transports

Metadata

Raise this grade

Add a badge to your README

Reviews

▶ Try itlive against doc.page

doc.page PDF ExtractionPublisher🛡 No advisories