Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
A remote Model Context Protocol server that gives any agent document-reading eyes: PDFs and images by URL β markdown (tables preserved) or plain text, with exact cost reporting and hard spend caps.
Hosted at https://mcp.pennyocr.com β nothing to install:
Keys are free (100 pages/month) at pennyocr.com/dashboard.
Clients that can't set headers: https://mcp.pennyocr.com/?key=pk_live_...
| Tool | Input | Output |
|---|---|---|
read_document | {url, pages?, output?, max_pages?, max_cost_usd?} | {content, pages, cost_usd, citations[]} |
estimate_cost | {url, pages?} | page count + exact cost β free |
The cost caps refuse before any processing, with the numbers β so autonomous agents can reason about spend ("200 pages, $0.15 β proceed") and can never run past a prepaid balance.
Streamable HTTP (JSON-RPC 2.0 over POST), stateless. This repo is the complete server β
a single Cloudflare Worker (worker.js) proxying the PennyOCR API.
Pricing: $0.75 per 1,000 pages Β· pennyocr.com/pricing.txt Β· Agent onboarding: pennyocr.com/llms.txt
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/ocr-3)<a href="https://allmcps.com/mcp/ocr-3"><img src="https://allmcps.com/api/badge/ocr-3?style=directory" alt="Ocr on AllMCPs" /></a>