Suparse Document Processing runs on your own machine — the client starts it, so there is no endpoint to ping. 132 installs a week from npm. Last commit 2 Jun 2026.
Extract structured data from PDFs and documents with Suparse AI OCR.
Today is the operative word: we check Suparse Document Processing every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add suparse-mcp -- npx -y @suparse/mcp
{
"mcpServers": {
"suparse-mcp": {
"args": [
"-y",
"@suparse/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.suparse-mcp]
command = "npx"
args = ["-y", "@suparse/mcp"]
{
"mcpServers": {
"suparse-mcp": {
"args": [
"-y",
"@suparse/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"suparse-mcp": {
"args": [
"-y",
"@suparse/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SUPARSE_API_KEY (Suparse API key used to authenticate requests.), SUPARSE_API_URL (Optional Suparse API base URL override.).
The author declared them in the registry entry; get the values from the project itself.
Parse and extract structured data from various document formats (PDF, Word, HTML).
Extract data, edit, convert, and parse PDF documents with OCR and AI
Extract structured data points from research papers and other documents with an LLM.
Turn documents into structured data: parse, extract, classify, split, and fill PDF forms.
MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
Professional document generation from structured data
Extract text from documents, manipulate PDFs, and perform OCR on images.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Answers built from our own checks of this server.