PennyOCR
Reads PDFs and images into agent context as markdown or plain text. $0.75 per 1,000 pages, exact per-call cost reporting, free cost estimator, spend caps. Hosted at mcp.pennyocr.com.
Documentation
๐ช PennyOCR MCP server
A remote Model Context Protocol server that gives any agent document-reading eyes: PDFs and images by URL โ markdown (tables preserved) or plain text, with exact cost reporting and hard spend caps.
Hosted at https://mcp.pennyocr.com โ nothing to install:
{
"mcpServers": {
"pennyocr": {
"url": "https://mcp.pennyocr.com",
"headers": { "Authorization": "Bearer pk_live_..." }
}
}
}
Keys are free (100 pages/month) at pennyocr.com/dashboard.
Clients that can't set headers: https://mcp.pennyocr.com/?key=pk_live_...
Tools
| 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 โ free |
The cost caps refuse before any processing, with the numbers โ so autonomous agents can reason about spend ("200 pages, $0.15 โ proceed") and can never run past a prepaid balance.
Transport
Streamable HTTP (JSON-RPC 2.0 over POST), stateless. This repo is the complete server โ
a single Cloudflare Worker (worker.js) proxying the PennyOCR API.
Pricing: $0.75 per 1,000 pages ยท pennyocr.com/pricing.txt ยท Agent onboarding: pennyocr.com/llms.txt