Document Parser runs on your own machine — the client starts it, so there is no endpoint to ping. 59 installs a week from npm. Last commit 2 Apr 2026.
Parse and extract structured data from various document formats (PDF, Word, HTML).
Nothing serious here today
Today is the operative word: we check Document Parser every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 document-parser -- npx -y @agenson-horrowitz/document-parser-mcp{
"mcpServers": {
"document-parser": {
"args": [
"-y",
"@agenson-horrowitz/document-parser-mcp"
],
"command": "npx"
}
}
}[mcp_servers.document-parser]
command = "npx"
args = ["-y", "@agenson-horrowitz/document-parser-mcp"]{
"mcpServers": {
"document-parser": {
"args": [
"-y",
"@agenson-horrowitz/document-parser-mcp"
],
"command": "npx"
}
}
}{
"mcpServers": {
"document-parser": {
"args": [
"-y",
"@agenson-horrowitz/document-parser-mcp"
],
"command": "npx"
}
}
}Alternatives to Document Parser
same job, measured the same wayExtract structured data from PDFs and documents with Suparse AI OCR.
Turn documents into structured data: parse, extract, classify, split, and fill PDF forms.
Extract structured data points from research papers and other documents with an LLM.
Extract data, edit, convert, and parse PDF documents with OCR and AI
Extract schema-valid JSON from text/HTML or document images. Pay per call via x402 V2.
Professional document generation from structured data
High-fidelity PDF to structured Markdown conversion and document field extraction.
Query Klaaro datasets, documents, and extracted records from any agent.
Document Parser — questions
Answers built from our own checks of this server.