com.pennyocr/ocr is an MCP server published by com.pennyocr, hosted at mcp.pennyocr.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 2 tools, including read_document, estimate_cost.
Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
Nothing else in the archive shares these values.
Read a document (PDF or image) from a URL and return its contents as markdown (tables preserved) or plain text. Costs $0.00075 per page, billed to the PennyOCR account; the response includes the exact cost_usd and per-page citations. Use estimate_cost first for big documents. Supports page ranges and hard spend caps.
| Parameter | Type | Description |
|---|---|---|
| url * | string | http(s) URL of the PDF or image |
| pages | string | Page range like '1-20,25'. Default: all pages. |
| output | string | Output format. Default markdown. |
| max_pages | integer | Refuse (with the numbers) if selection exceeds this many pages. |
| max_cost_usd | number | Refuse (with the numbers) if the run would cost more than this. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
{
"name": "read_document",
"description": "Read a document (PDF or image) from a URL and return its contents as markdown (tables preserved) or plain text. Costs $0.00075 per page, billed to the PennyOCR account; the response includes the exact cost_usd and per-page citations. Use estimate_cost first for big documents. Supports page ranges and hard spend caps.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "http(s) URL of the PDF or image"
},
"pages": {
"type": "string",
"description": "Page range like '1-20,25'. Default: all pages."
},
"output": {
"enum": [
"markdown",
"text"
],
"type": "string",
"description": "Output format. Default markdown."
},
"max_pages": {
"type": "integer",
"description": "Refuse (with the numbers) if selection exceeds this many pages."
},
"max_cost_usd": {
"type": "number",
"description": "Refuse (with the numbers) if the run would cost more than this."
}
}
}
}Free: return the page count and exact cost_usd to read a document URL with read_document, without running OCR. Use before reading large documents.
| Parameter | Type | Description |
|---|---|---|
| url * | string | http(s) URL of the PDF or image |
| pages | string | Optional page range like '1-20'. |
{
"name": "estimate_cost",
"description": "Free: return the page count and exact cost_usd to read a document URL with read_document, without running OCR. Use before reading large documents.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "http(s) URL of the PDF or image"
},
"pages": {
"type": "string",
"description": "Optional page range like '1-20'."
}
}
}
}PennyOCR reads documents (PDF/images) into markdown or text. read_document costs $0.00075/page (exact cost_usd returned); estimate_cost is free. Get an API key at https://pennyocr.com/dashboard/ — agents: see https://pennyocr.com/llms.txt for keyless signup steps.
Names, descriptions and schemas were written by the server and are shown as data.