* * * DOCUMENT READER MCP * * *

A Document Reader MCP Server.

Your agent hits a PDF link and goes blind. Give it eyes: mcp.pennyocr.com exposes read_document — any PDF or image by URL, returned as markdown with per-page citations and the exact cost — plus a free estimate_cost so it never commits blind to a 500-page bill.

START FREE — 50 PAGES
$0.75 / 1,000 PAGES
1,333 PAGES PER DOLLAR · NO CREDIT CARD
AT A GLANCE
UPDATED
PRICE
$0.75 per 1,000 pages ($0.00075 per page), prepaid
FREE TIER
First 50 pages free per account, no credit card
FORMATS
PDF, PNG, JPEG, WebP, TIFF
LIMITS
50 MB and 500 pages per request
OUTPUT
JSON with markdown (tables preserved) or plain text, per page and joined
INTERFACES
REST API, OpenAI-compatible chat completions, MCP server
CREDITS
Never expire; requests stop with a 402 when the balance runs out
01 / TRY IT

ONE ENDPOINT.

POST a file, get JSON back — the extracted text, per page and joined. PDF, PNG, JPEG, WebP or TIFF.

curl https://api.pennyocr.com/v1/ocr \
  -H "Authorization: Bearer $PENNYOCR_API_KEY" \
  -F "file=@contract.pdf"

# $0.75 per 1,000 pages, first 50 free
02 / USE CASES

WHAT AGENTS DO WITH IT.

RESEARCH AGENTS
Follow citations into PDFs: estimate, read pages 1-20, quote with page numbers.
FINANCE WORKFLOWS
Statements and invoices in email or cloud storage become structured markdown an agent can reconcile.
COMPLIANCE REVIEW
Contracts read page-by-page with citations that survive into the final memo.
COST-AWARE LOOPS
Set max_cost_usd per call and let the agent run unattended — worst case is your prepaid balance.
03 / PRICE CHECK

HALF THE PRICE OF THE BIG CLOUDS.

Per 1,000 pages, public list prices, first tier.

PENNYOCR$0.75
AWS TEXTRACT$1.50
GOOGLE CLOUD VISION$1.50
AZURE DOC INTELLIGENCE$1.50
YOU KEEP50%
04 / FAIR QUESTIONS
GET YOUR API KEY →
QUESTIONS? HELLO@PENNYOCR.COM
SETUP IN ONE BLOCK?
{"mcpServers": {"pennyocr": {"url": "https://mcp.pennyocr.com", "headers": {"Authorization": "Bearer pk_live_..."}}}}. Full details at pennyocr.com/mcp.
DOES IT HANDLE SCANS AND PHOTOS?
Yes — it's OCR underneath (a vision-language model), so scanned PDFs, photos and screenshots read the same as digital PDFs.
WHAT IF THE URL NEEDS AUTH?
Today read_document fetches public/presigned URLs. For private files, upload via the REST API's multipart endpoint instead.