Wraps the OCR.space API to extract text from images and PDFs directly in your MCP client. The source documentation is light on tool specifics, but this is a straightforward gateway to OCR.space's optical character recognition service through Pipeworx's hosted MCP infrastructure. You can either add this individual server or connect to the full Pipeworx gateway for access to 748+ data sources. Includes an ask_pipeworx tool that lets you make plain English queries instead of calling structured APIs directly. Useful when you need to pull text from screenshots, scanned documents, or PDFs without leaving your AI workflow.
OCR.space MCP — wraps the OCR.space API (ocr.space) for image/PDF → text OCR.
Part of Pipeworx — an MCP gateway connecting AI agents to 748+ live data sources.
| Tool | Description |
|---|
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"ocrspace": {
"url": "https://gateway.pipeworx.io/ocrspace/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 748+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Ocrspace data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
csoai-org/pdf-document-mcp
xt765/mcp-document-converter
io.github.ai-aviate/better-notion
suekou/mcp-notion-server
meterlong/mcp-doc
n24q02m/better-notion-mcp