* * * MODEL CONTEXT PROTOCOL * * *

The PennyOCR MCP Server.

One config block and your agent reads documents. Add this to your MCP client — Claude Desktop/Code, OpenAI Agents SDK, Cloudflare Agents, anything speaking Streamable HTTP: {"mcpServers": {"pennyocr": {"url": "https://mcp.pennyocr.com", "headers": {"Authorization": "Bearer pk_live_..."}}}} — keys are free at pennyocr.com/dashboard.

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=@report.pdf"

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

TWO TOOLS, NO FLUFF.

READ_DOCUMENT
{url, pages?, output?, max_pages?, max_cost_usd?} → {content, pages, cost_usd, citations[]}. Markdown with tables by default, plain text on request.
ESTIMATE_COST
{url, pages?} → exact page count and cost_usd, free. Lets the agent decide before committing to a 500-page read.
PER-PAGE CITATIONS
citations[] maps output back to page numbers, so downstream answers can reference 'page 14' honestly.
CLIENTS WITHOUT HEADERS
Use https://mcp.pennyocr.com/?key=pk_live_... when your MCP client can't set headers.
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
WHAT DOES IT COST?
Same as the API: $0.00075 per page, from your prepaid balance, first 50 pages free. Every read_document response reports the exact cost_usd it consumed.
WHICH TRANSPORT?
Streamable HTTP (JSON-RPC 2.0 over POST). No SSE requirement, no session state — stateless and cache-friendly.
IS MY DATA STORED?
Zero retention by default: documents are fetched, read, returned and discarded. Storage is opt-in from the dashboard.