OCR.space logo
ConnectorOCR.space

OCR.space integration for Claude and Codex

Connect OCR.space once, then control which Spaces can use its approved tools and data without pasting credentials into prompts or threads.

Use OCR.space from Claude

Add the OCR.space connection to a Space that runs Claude, then use it from every channel in that Space.

Use OCR.space from Codex

Add the OCR.space connection to a Space that runs Codex, then use it from every channel in that Space.

Use OCR.space from Sidekick

Connect your own OpenClaw to Sidekick while type.com provides the conversations, permissions, connections, skills, and automations.

Analytics & Data

What the OCR.space connector can do

OCR.space extracts text from images and PDFs, supporting dozens of languages and table recognition. A document or operations Space in type.com can ask Claude to pull text out of a scanned invoice, grab text from an image URL directly, or check how many conversions the account has used this month.

One connection, many Spaces

Connect OCR.space once, then decide which Spaces can use it in threads, skills, automations, and coding work.

What teams do with OCR.space in type.com

Pull text from a scanned document

Extract text from an uploaded PDF or image, including tables, instead of retyping a scanned invoice by hand.

Try asking
Extract the text from this scanned invoice PDF using OCR.space and pull out the total amount.

Grab text straight from an image link

Run OCR on an image URL directly when the file is already hosted online, skipping an upload step.

Try asking
Extract the text from this receipt image URL using OCR.space.

Check monthly conversion usage

Review how many OCR conversions the account has used so far this month before a large batch job.

Try asking
Check our OCR.space conversion statistics for this month before I submit another batch of scans.

Representative actions

  • Get Conversion Statistics

    Returns the number of OCR conversions used this month, broken down by engine, for PRO accounts.

  • Extract Text from Image/PDF (OCR)

    Extracts text from an uploaded image or PDF, with options for language, table recognition, and orientation detection.

  • Extract Text from Image URL (GET)

    Extracts text from an image hosted at a URL using a simpler, faster request than the file-upload endpoint.

Connection

API and auth details

OCR.space provides free and paid OCR APIs for extracting text from images, PDFs, and remote URLs. Integrations can request OCR in JSON, specify language and detection options, process searchable PDFs, use overlay data, and authenticate with API keys.

Source
type.com catalog metadata
Auth schemes
API key
Official site
https://ocr.space/
FAQ

Questions people ask before connecting OCR.space

Can Claude pull text out of scanned documents?

Yes. Once an OCR.space connection is shared with a type.com Space, the agent can extract text from uploaded files or image URLs directly in a thread.

How do I authenticate OCR.space in type.com?

OCR.space uses an API key. An admin adds it once when creating the connection, then controls which Spaces can use it.

Can type.com process scanned documents on a schedule?

Yes. An automation can watch for new scans and run OCR.space on them automatically, posting extracted text to a channel.

Is this the same as an MCP server for OCR.space?

Not exactly. type.com uses connectors and connections to give selected Spaces access to approved app tools and data. Some connectors use hosted MCP, while others use OAuth, API keys, service accounts, or custom APIs.

More analytics & data connectors

All Analytics & Data integrations