PennyOCR MCP MCP server
An official MCP server provided by PennyOCR that enables AI agents to extract text from documents such as PDFs, images, and scans. It supports reading documents with citation mapping to page numbers, estimating costs before processing, and handling various file formats like PNG, JPEG, and TIFF. The server integrates with Streamable HTTP and allows agents to make informed decisions about document processing based on exact pricing and page counts.
Endpoint and access
No sign-in: your client connects and lists tools immediately, with no account or key.
https://mcp.pennyocr.comWhat you can do with it
- Extract text and tables from PDFs and images into markdown
- Estimate page count and cost before processing a document
- Map extracted text back to specific page numbers for citations
read_documentestimate_cost
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http pennyocr-mcp https://mcp.pennyocr.comCodex
codex mcp add pennyocr-mcp --url https://mcp.pennyocr.comCursor
{
"mcpServers": {
"pennyocr-mcp": {
"url": "https://mcp.pennyocr.com"
}
}
}Cline
{
"mcpServers": {
"pennyocr-mcp": {
"type": "streamableHttp",
"url": "https://mcp.pennyocr.com",
"disabled": false
}
}
}VS Code
{
"servers": {
"pennyocr-mcp": {
"type": "http",
"url": "https://mcp.pennyocr.com"
}
}
}Gemini CLI
gemini mcp add --transport http pennyocr-mcp https://mcp.pennyocr.comClaude Desktop
{
"mcpServers": {
"pennyocr-mcp": {
"url": "https://mcp.pennyocr.com"
}
}
}Windsurf
{
"mcpServers": {
"pennyocr-mcp": {
"serverUrl": "https://mcp.pennyocr.com"
}
}
}Other ai and machine learning servers
Do you run PennyOCR MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.