split_pdf

pdf

Split a PDF into one file per page. Each page comes back as its own short-TTL signed download URL.

When to use: The user wants every page of a PDF as its own file.
Not for: Pulling out a specific page range and keeping one PDF (pdf_operation with operation 'extract-pages'). Turning pages into images (convert_file with target_format 'jpg').
Returns: A list of files, one per page, each with a filename and a signed download URL.

Parameters

Name	Type	Required	Description
file_url	string	no	Public http(s) URL of the input file (preferred — fetched server-side, so the bytes never pass through your context). Private, loopback and cloud-metadata addresses are blocked.
file_base64	string	no	Base64 of a small inline input file (up to about 15MB). Provide "filename" too.
filename	string	no	Original filename including its extension, e.g. "report.pdf". The extension is how the source format is detected.
output_base_name	string	no	Base name for the produced files, e.g. "invoice" gives invoice-1.pdf, invoice-2.pdf.

Example call

JSON-RPC tools/call body (sent to https://convertfleet.com/api/mcp):

{
  "jsonrpc": "2.0", "id": 1, "method": "tools/call",
  "params": { "name": "split_pdf", "arguments": {
               "file_url": "https://example.com/input"
             } }
}

Connect first

curl -sN https://convertfleet.com/api/mcp \
  -H "Authorization: Bearer flt_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

See the quickstarts for Hermes, Claude, Cursor, OpenClaw, n8n, Zapier and Make.