OCR is answering right now. Last checked 11 min ago. It exposes 2 tools. Last commit 30 Aug 2026.
Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
Nothing serious here today
Today is the operative word: we check OCR 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
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add ocr --transport http https://mcp.pennyocr.com{
"mcpServers": {
"ocr": {
"url": "https://mcp.pennyocr.com"
}
}
}[mcp_servers.ocr]
url = "https://mcp.pennyocr.com"{
"mcpServers": {
"ocr": {
"url": "https://mcp.pennyocr.com"
}
}
}{
"mcpServers": {
"ocr": {
"url": "https://mcp.pennyocr.com"
}
}
}Available tools 2
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
read_document
estimate_cost
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.pennyocr.com | streamable-http | answering | 90 ms | 11 min ago |
Alternatives to OCR
same job, measured the same wayRender HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
Publish HTML, Markdown, PDF, or images as instant shareable links with expiry and passwords.
Agent-facing PDF API: merge, split, rotate, compress, images, metadata, text, and Markdown.
Read, convert and fill Word (.docx) documents: templates, Markdown/HTML in and out, PDF with math.
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
Operate Notion with a single Markdown document — read, create, and update pages in one call.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
OCR — questions
Answers built from our own checks of this server.