Apdf — PDF Tracking & Reader Analytics

The PDF engagement layer for apps and agents.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • List Documents: List documents. Returns active documents by default; pass "status" to include archived. Supports paging via "page" and "per_page".
  • Get Document: Get a single document by its public id.
  • Create Document: Create a trackable document from a PDF URL.

What data it sees

Do you need an account

No: the server works without sign-in

The PDF engagement layer for apps and agents. Share documents as per-recipient tracking links, then query page-level read analytics, viewer sessions, form submissions and annotations. Includes a full PDF toolset: create, merge, split, compress, convert and encrypt. 40+ tools, one OAuth endpoint.

How to connect

How to connect Apdf — PDF Tracking & Reader Analytics to Claude

The server address to paste into Claude settings:

https://main--apdf.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Apdf — PDF Tracking & Reader Analytics to ChatGPT

The server address to paste into ChatGPT settings:

https://main--apdf.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Apdf — PDF Tracking & Reader Analytics to Cursor

The server address to paste into Cursor settings:

https://main--apdf.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (45)

Raw names from tools/list. Only developers need these.

list-documentsList documents. Returns active documents by default; pass "status" to include archived. Supports paging via "page" and "per_page".
get-documentGet a single document by its public id.
create-documentCreate a trackable document from a PDF URL.
delete-documentDelete a document (and its underlying PDF file) by its public id.
archive-documentArchive a document by its public id. Archived documents stop counting toward the workspace's tracked-documents quota and become inert. Reversible via "unarchive-document".
unarchive-documentRestore a previously archived document. The document becomes active again and counts toward the workspace's tracked-documents quota.
make-document-publicMake a document public by its public id, so it can be viewed without a recipient link. Reversible via "make-document-private".
make-document-privateMake a document private by its public id, so it only opens through a valid recipient link. Reversible via "make-document-public".
list-document-linksList all recipient links for a document. Supports paging via "page" and "per_page".
create-document-linkCreate a new recipient link for a document.
delete-document-linkDelete a document link by its token.
activate-document-linkActivate (enable) a recipient link by its token. Reversible via "deactivate-document-link".
deactivate-document-linkDeactivate (disable) a recipient link by its token. Reversible via "activate-document-link".
list-document-annotationsList annotations for a document. Supports paging via "page" and "per_page".
list-document-form-submissionsList form submissions for a document. Supports paging via "page" and "per_page".
get-document-analyticsGet aggregate KPIs (sessions, viewers, completion rate, downloads, ...) for a document.
list-document-sessionsList viewing sessions for a document with per-session metrics. Supports paging via "page" and "per_page".
get-document-sessionGet full detail (events, metrics, page-by-page breakdown) for a single viewing session.
list-automationsList all automations. Supports paging via "page" and "per_page".
get-automationGet a single automation by its id, including its trigger, conditions and webhook action.
create-automationCreate a when/filter/then rule that posts reader events to a webhook. The automation starts out active.
delete-automationDelete an automation and its execution history. To keep the rule and only stop it from firing, use "deactivate-automation".
activate-automationActivate (enable) an automation so it fires again. Counts against the active-automations limit. Reversible via "deactivate-automation".
deactivate-automationDeactivate (pause) an automation so it stops firing. The rule and its execution history are kept. Reversible via "activate-automation".
duplicate-automationCopy an automation with its trigger, conditions, webhook and documents. The copy is named after the original with "(Copy)" appended and starts out active.
list-automation-executionsList all automation executions. Each entry includes the matched event, the payload sent and the endpoint response. Supports paging via "page" and "per_page".
create-pdf-fileCreate a PDF from the given HTML and return its hosted URL. Always runs asynchronously and returns a job id; poll "check-job-status" or provide "webhook_url" to receive a callback.
split-pdf-fileSplit a PDF file into multiple files using a page-range expression (e.g. "1-3,4-6" for explicit ranges or "n3" for fixed chunks of 3 pages).
merge-pdf-filesMerge multiple PDF files (optionally limited to a page-range each) into a single PDF.
compress-pdf-fileCompress a PDF file to reduce its file size. Always runs asynchronously and returns a job id; poll "check-job-status" or provide "webhook_url" to receive a callback.
convert-pdf-to-imageRender PDF pages as images (PNG/JPG/...) at a given DPI. Always runs asynchronously and returns a job id; poll "check-job-status" or provide "webhook_url" to receive a callback.
extract-pdf-pagesExtract a subset of pages from a PDF and return the result as a new PDF.
delete-pdf-pagesDelete a subset of pages in a PDF and return the resulting PDF without those pages.
rotate-pdf-pagesRotate one or more pages in a PDF by a multiple of 90 degrees.
overlay-pdf-pagesOverlay another PDF on top of pages of a base PDF (e.g. for watermarks above content).
underlay-pdf-pagesUnderlay another PDF beneath pages of a base PDF (e.g. for backgrounds behind content).
search-pdf-contentSearch for text in a PDF file and return the matches with their positions.
read-pdf-contentExtract the textual content of a PDF file, page by page.
convert-pdf-with-ocrRun OCR over a scanned PDF and return a searchable PDF with embedded text. Always runs asynchronously and returns a job id; poll "check-job-status" or provide "webhook_url" to receive a callback.
search-pdf-content-with-ocrOCR a scanned PDF and search for text in it. Always runs asynchronously and returns a job id; poll "check-job-status" or provide "webhook_url" to receive a callback. The completed job result contains matches with their positions.
read-pdf-content-with-ocrOCR a scanned PDF and return the extracted textual content, page by page. Always runs asynchronously and returns a job id; poll "check-job-status" or provide "webhook_url" to receive a callback.
add-pdf-securityAdd password-based security restrictions (owner / optional user password) to a PDF.
remove-pdf-securityRemove password-based security restrictions from a PDF.
read-pdf-metadataRead metadata (title, author, page count, file size, ...) from a PDF file.
check-job-statusCheck the status (and result, if any) of an asynchronous api job by its id.